Cognitive effectiveness dynamic evaluation, regulation and control method for training trainees and related equipment thereof

Abstract

The invention provides a cognitive performance dynamic evaluation, regulation and control method for training trainees and related equipment thereof. The method comprises the following steps: acquiring multi-source original data of a target object; performing feature construction on the multi-source original data based on the multi-source original data through a preset cognitive performance model to generate a plurality of cognitive performance index parameters, and allocating a weight coefficient for each index parameter to obtain a cognitive performance calculation data set; performing weighted calculation on the cognitive performance calculation data set through a preset performance calculation model to obtain a cognitive performance comprehensive score of the target object; generating a target cognitive performance portrait corresponding to the target object based on the cognitive performance comprehensive score; and based on the target cognitive performance portrait, determining a personalized intervention strategy of the target object, and performing intervention regulation and control on the target object according to the personalized intervention strategy. By means of the method, the cognitive state difference of the target object can be accurately described based on the multi-dimensional data, targeted dynamic intervention is achieved, and the accuracy and effectiveness of cognitive performance evaluation are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent training optimization, and in particular to a method, device, electronic device and storage medium for dynamic evaluation and control of trainees' cognitive effectiveness. Background Technology

[0002] Cognitive efficacy refers to the comprehensive performance of an individual in terms of psychological state, behavioral input, and output during cognitive activities. It is used to measure an individual's overall ability in cognitive processing, learning execution, task participation, and outcome transformation. With the digital upgrade of education and training, talent cultivation, and competency assessment systems, the measurement and management of cognitive efficacy is gradually evolving from single-dimensional assessment to multi-dimensional integration. This requires not only focusing on an individual's subjective cognition but also combining behavioral performance and output to achieve a more comprehensive and objective identification of competency and decision-making for improvement.

[0003] Existing methods for assessing cognitive efficacy largely rely on static scales, single assessments, or fixed intervention procedures. These methods suffer from limited data sources and insufficient utilization of behavioral and outcome information, making it difficult to develop assessment models that accurately reflect an individual's long-term cognitive state. Furthermore, existing intervention mechanisms are often based on uniform rules or fixed strategies, lacking the ability to differentiate for different cognitive characteristics and a dynamic adjustment mechanism based on continuous assessment results. This leads to a disconnect between assessment results and intervention effectiveness, failing to achieve sustained cognitive improvement throughout an individual's growth process.

[0004] Therefore, existing methods for dynamic assessment and regulation of trainees' cognitive efficacy have the problem of being unable to achieve accurate profiling and personalized strategy regulation based on multi-source data. Summary of the Invention

[0005] This invention provides a method for dynamic assessment and regulation of trainees' cognitive efficacy, in order to solve the problem that existing methods for dynamic assessment and regulation of trainees' cognitive efficacy cannot achieve accurate profiling and personalized strategy regulation based on multi-source data.

[0006] In a first aspect, the present invention provides a method for dynamic assessment and regulation of trainees' cognitive efficacy, the method comprising the following steps: Obtain multi-source raw data of the target object; Based on the multi-source raw data, a pre-set cognitive efficacy model is used to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters, and weight coefficients are assigned to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset. By using a preset performance calculation model, the cognitive performance calculation dataset is weighted and calculated to obtain the comprehensive cognitive performance score of the target object; Based on the comprehensive cognitive efficacy score, a target cognitive efficacy profile corresponding to the target object is generated. Based on the target cognitive efficacy profile, a personalized intervention strategy is determined for the target object, and intervention and regulation are performed on the target object according to the personalized intervention strategy.

[0007] Optionally, obtaining the multi-source raw data of the target object includes: Periodic assessment data of the target object are collected to obtain psychological assessment data; Periodic objective behavioral data of the target object are collected to obtain behavioral record data; Periodic performance data of the target object are collected to obtain performance data; The psychological assessment data, behavioral record data, and performance data are preprocessed to obtain multi-source raw data.

[0008] Optionally, the step of generating multiple cognitive efficacy index parameters by constructing features from the multi-source raw data based on the preset cognitive efficacy model includes: Determine the performance characteristics of each dimension in the multi-source raw data, wherein the performance characteristics are used to reflect the performance expression form corresponding to the raw data in different dimensions; Based on the efficacy characteristics of each dimension, feature construction is performed on the multi-source raw data to generate multiple corresponding cognitive efficacy index parameters.

[0009] Optionally, the step of assigning weight coefficients to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset includes: Determine the feature distribution data corresponding to each of the cognitive efficacy index parameters; Based on the feature distribution data corresponding to each cognitive efficacy index parameter, the weight coefficients corresponding to each cognitive efficacy index parameter are determined. By matching and combining the parameters of each cognitive efficacy index with their corresponding weight coefficients, a cognitive efficacy calculation dataset is obtained.

[0010] Optionally, the step of performing a weighted calculation on the cognitive efficacy calculation dataset using a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object includes: Based on the values ​​of each cognitive efficacy index parameter and its corresponding weight coefficient in the cognitive efficacy calculation dataset, feature weighting and parameter fusion processing are performed to obtain the efficacy calculation result. Based on the performance calculation results, a comprehensive cognitive performance score for the target object is generated.

[0011] Optionally, generating a target cognitive efficacy profile for the target object based on the comprehensive cognitive efficacy score includes: Based on the comprehensive cognitive efficacy score, determine the score data corresponding to each cognitive efficacy indicator parameter; Based on the score data, the performance characteristics of the current target object are displayed in a hierarchical manner and visualized to generate a corresponding target cognitive performance profile. The cognitive performance profile is used to reflect the performance differences between the various dimensional indicator parameters of the target object.

[0012] Optionally, determining a personalized intervention strategy for the target object based on the target cognitive efficacy profile, and performing intervention and regulation on the target object according to the personalized intervention strategy, includes: Based on the target cognitive efficacy profile, the negative cognitive efficacy index parameters of the target object are determined; Based on the aforementioned disadvantage cognitive efficacy index parameters, at least one corresponding intervention strategy is matched from the preset strategy library. Based on the at least one corresponding intervention strategy, a personalized intervention strategy is generated, and intervention and regulation are performed on the target object.

[0013] Secondly, the present invention also provides a device for dynamic assessment and regulation of cognitive efficacy of trainees, the device comprising: The first acquisition module is used to acquire multi-source raw data of the target object; The first construction module is used to generate multiple cognitive efficacy index parameters by performing feature construction on the multi-source raw data based on the multi-source raw data through a preset cognitive efficacy model, and to assign weight coefficients to each index parameter to obtain a cognitive efficacy calculation dataset. The first calculation module is used to perform weighted calculation on the cognitive efficacy calculation dataset through a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object. The first generation module is used to generate a cognitive efficacy profile corresponding to the target object based on the comprehensive cognitive efficacy score. The first determining module is used to determine a personalized intervention strategy for the target object based on the target cognitive efficacy profile, and to perform intervention and regulation on the target object according to the personalized intervention strategy.

[0014] Thirdly, the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the method for dynamic assessment and regulation of cognitive efficacy of trainees provided by the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps in the method for dynamic assessment and regulation of cognitive efficacy of trainees provided by the invention.

[0016] This invention acquires multi-source raw data of the target object; based on the multi-source raw data, a pre-set cognitive efficacy model is used to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters, and weight coefficients are assigned to each index parameter to obtain a cognitive efficacy calculation dataset; the cognitive efficacy calculation dataset is weighted and calculated using the pre-set efficacy calculation model to obtain the target object's comprehensive cognitive efficacy score; based on the comprehensive cognitive efficacy score, a target cognitive efficacy profile corresponding to the target object is generated; based on the target cognitive efficacy profile, a personalized intervention strategy is determined for the target object, and intervention and regulation are implemented for the target object according to the personalized intervention strategy. Through the above method, the differences in the cognitive state of the target object can be accurately characterized based on multi-dimensional data, enabling targeted dynamic intervention and improving the accuracy and effectiveness of cognitive efficacy assessment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a method for dynamically assessing and regulating the cognitive efficacy of trainees, provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of another device for dynamically assessing and regulating the cognitive efficacy of trainees provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, Figure 1This is a flowchart of a method for dynamically assessing and regulating the cognitive efficacy of trainees, provided by an embodiment of the present invention. The method includes the following steps: 101. Obtain multi-source raw data of the target object.

[0021] In this embodiment of the invention, the above-mentioned method for dynamic evaluation and regulation of trainees' cognitive efficacy can be applied to a platform for dynamic evaluation and regulation of trainees' cognitive efficacy. The platform has functions such as training evaluation and adjustment data processing, training evaluation and adjustment data sending and receiving, and training evaluation and adjustment data memory storage. It can be built based on a server or server cluster. The server or server cluster can be an electronic device with training evaluation and adjustment data processing capabilities.

[0022] The aforementioned target group can refer to trainees who need to undergo training and cognitive efficacy assessment. Specifically, the cognitive efficacy dynamic assessment and regulation platform for the aforementioned trainees can collect and assess data on the psychological state, learning behavior and performance of the aforementioned target group during the learning process, and generate corresponding cognitive efficacy profiles and intervention measures.

[0023] The aforementioned multi-source data can refer to a collection of multiple categories of data related to trainees' cognitive efficacy, including but not limited to periodic psychological assessment data, records of learning or activity participation behavior, and information on training performance and practical results. It is understood that this multi-source data can be obtained by collecting data from trainees' training systems, questionnaire assessments, or outcome registration systems, and then preprocessing the data.

[0024] 102. Based on multi-source raw data, a pre-set cognitive efficacy model is used to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters. Weight coefficients are assigned to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset.

[0025] In this embodiment of the invention, the aforementioned preset cognitive efficacy model can be a structured representation model used to transform multi-source data into computable dimensions. It includes multiple feature extraction methods, such as: psychological factor extraction (e.g., emotional stability, confidence index mapping); behavioral pattern modeling (e.g., execution regularity, temporal analysis of engagement, intensity of behavioral activities); and achievement level mapping (e.g., achievement level, conversion ability, sustained contribution). It is understood that the aforementioned preset cognitive efficacy model is set during the initialization of the cognitive efficacy dynamic assessment and control platform for the trainees, thereby ensuring that the indicators for different trainees can be constructed under unified rules, guaranteeing the comparability and repeatability of the assessment results.

[0026] The aforementioned feature construction and generation can refer to the process of transforming complex and disordered raw data into standardized, computable numerical features. Specifically, the aforementioned training participants' cognitive efficacy dynamic assessment and regulation platform can perform the transformation through the following steps: normalizing the raw data, converting standard scores, and quantifying the scores; performing time-domain statistics (frequency, duration, volatility) on behavioral data; ranking, weighting, and extracting trends from the outcome data; and finally converting psychological, behavioral, and outcome data into quantifiable efficacy feature values.

[0027] The aforementioned cognitive efficacy indicators can be numerical representations of differences in cognitive abilities, formed after feature construction. Examples include: psychological indicators such as self-efficacy index, emotional stability coefficient, and satisfaction level; behavioral indicators such as course participation activity, behavioral consistency index, and executive function score; and outcome indicators such as learning outcome output index, practical contribution coefficient, and growth slope value.

[0028] The aforementioned weighting coefficients can represent the degree of influence of each indicator parameter on comprehensive cognitive ability. In one possible embodiment, the aforementioned dynamic assessment and control platform for trainees' cognitive efficacy can automatically calculate the weights based on data characteristic distribution. For example, indicators with small statistical fluctuations and stable contributions will have their weights increased; indicators that are significantly correlated with comprehensive efficacy will have their weights increased; and indicators with large instantaneous fluctuations and weak interpretability will have their weights decreased. Therefore, it can be understood that the weighting coefficients are dynamically adjustable, and the aforementioned dynamic assessment and control platform for trainees' cognitive efficacy can recalculate them based on reassessment data after intervention, thereby reflecting the stage changes in trainees' ability development.

[0029] The aforementioned cognitive efficacy calculation dataset can be used to represent a structured input package of "all indicator parameters of a student + corresponding weight coefficients" as input to the subsequent preset efficacy calculation model. Specifically, the aforementioned cognitive efficacy calculation dataset can transform the student's various ability scores into a unified structure for calculating the student's overall cognitive efficacy level, and can compare data from other dimensions through the bound weights.

[0030] In one possible embodiment, the above-mentioned training trainees’ cognitive efficacy dynamic assessment and regulation platform acquires the psychological assessment data, behavioral record data and performance data corresponding to the target object through the data acquisition module, and performs noise reduction, structure transformation and normalization on the above data to form multi-source raw data that can be used for model calculation. A pre-defined cognitive efficacy model is invoked to perform feature construction operations on multi-source raw data. Specifically, based on the performance structure of different categories of data, the pre-defined cognitive efficacy model extracts psychological state features, behavioral participation features, and outcome output features. For example, factor transformation is performed on psychological assessment data to obtain numerical parameters such as self-efficacy level and stability level; frequency statistics and continuity analysis are performed on behavioral data to obtain behavioral engagement and behavioral consistency parameters; and grade mapping and trend extraction are performed on outcome data to obtain outcome contribution level and growth curve change coefficient. The parameters after feature construction collectively form multiple cognitive efficacy index parameters, used to characterize the multidimensional performance of the target object in cognitive ability. Based on the stability, relevance, and performance contribution of each indicator parameter in the sample data, corresponding weight coefficients are calculated and assigned to ensure that different indicators have a weight proportion that reflects their actual impact in the subsequent comprehensive evaluation. Finally, the platform combines multiple cognitive efficacy indicator parameters with their corresponding weight coefficients to obtain a cognitive efficacy calculation dataset for subsequent comprehensive efficacy calculation.

[0031] Through the above methods and steps, complex multi-source raw data can be transformed into a structured indicator system, and the influence of different dimensions on cognitive efficacy can be accurately reflected by dynamic weights, making the comprehensive calculation process more consistent with the actual development characteristics of the target object.

[0032] 103. By using a preset efficacy calculation model, the cognitive efficacy calculation dataset is weighted and calculated to obtain the comprehensive cognitive efficacy score of the target object.

[0033] In this embodiment of the invention, the above-mentioned preset efficacy calculation model can be used to perform cognitive efficacy weighted calculation on the calculation dataset, including weight mapping, feature fusion and score conversion. Generally, linear weighting, weighted regression model, multivariate combination algorithm and other methods can be used to obtain a stable and reliable comprehensive cognitive efficacy score.

[0034] In this embodiment, the indicator parameters can be fused according to their weights using the aforementioned preset performance calculation model. That is, the "performance of different indicators × weight of different indicators" can be calculated in a unified manner to obtain the comprehensive cognitive performance score of the target object.

[0035] The aforementioned cognitive efficacy score can be used as a comprehensive cognitive performance value for the target subject, used to characterize the overall ability level of trainees in multiple dimensions of psychology, behavior and outcomes, and can serve as a basis for matching intervention strategies.

[0036] 104. Based on the comprehensive cognitive efficacy score, generate a target cognitive efficacy profile corresponding to the target object.

[0037] In this embodiment of the invention, the aforementioned target cognitive efficacy profile can be a visual representation of cognitive efficacy characteristics, including scores for each indicator dimension, differences in strength and weakness, and overall efficacy level. The profile can be presented graphically, using level labels, and difference comparisons to assist in assessing an individual's current strengths and weaknesses and guide intervention directions.

[0038] Specifically, it can be calculated using the following formula for generating self-efficacy: SES = α * P + β * C + γ * M Among them, SES is the comprehensive cognitive efficacy score, P is the work participation score, C is the activity integration score, M is the psychological capital level score, α, β, γ are the weight coefficients of each dimension, and α + β + γ = 1. The weights can be determined through the above dynamic settings. The above-mentioned cognitive efficacy dynamic assessment and control platform can automatically generate a personal "goal cognitive efficacy profile" of student party members based on the SES score and sub-item scores, and visualize their strengths and weaknesses in the form of radar charts, etc.

[0039] 105. Based on the target cognitive efficacy profile, determine the personalized intervention strategy for the target object, and implement intervention and regulation for the target object according to the personalized intervention strategy.

[0040] In this embodiment of the invention, the personalized intervention strategies described above can be the result of matching, combining, and adjusting strategies based on the disadvantage indicators identified through profile analysis. For example, for psychological deficiencies, psychological counseling, motivational tasks, and mindset cultivation courses can be recommended; for behavioral deficiencies, task execution training and participation in behavioral incentive mechanisms can be recommended; for achievement deficiencies, ability enhancement courses, practical experience accumulation, and evaluation and supervision mechanisms can be recommended. It is understood that the personalized intervention strategies described above can be derived from a pre-set strategy library and can be combined and optimized based on the profile.

[0041] In one possible embodiment, the aforementioned cognitive efficacy dynamic assessment and regulation platform for trainees performs operations such as course recommendation, behavioral incentives, and progress monitoring for target subjects based on personalized strategies. After the intervention is completed, data is re-collected, indicator parameters and weight coefficients are reconstructed, and the comprehensive score and profile are updated. Specifically, based on the latest periodic collected psychological assessment data, behavioral record data, and performance data, the corresponding cognitive efficacy indicator parameters are regenerated, and the weight coefficients and comprehensive efficacy scores are updated to form a cognitive efficacy profile again. Based on this, the original intervention strategy is adjusted or replaced.

[0042] By following the above methods and steps, we can continuously track changes in the target's abilities and adjust the direction of intervention accordingly, ensuring that the training process aligns with cognitive development trends, improving the effectiveness and adaptability of intervention measures, and further enhancing the stability and quality of cognitive efficacy improvement.

[0043] In another possible embodiment, the aforementioned cognitive efficacy dynamic assessment and regulation platform for trainees matches corresponding intervention measures from the strategy library based on the disadvantage indicator parameters identified in the target cognitive efficacy profile. According to the strategy requirements, it pushes course tasks, behavioral guidance, achievement supervision or incentive stimulation and other regulatory content to the target. The progress of behavioral execution, changes in psychological state and output are used as the tracking basis for intervention execution. The platform continuously records the changes in the target's performance during the intervention period to confirm the intervention execution and regulation effect.

[0044] By following the above methods and steps, targeted reinforcement can be implemented for different skill gaps, ensuring that regulatory measures correspond to individual weaknesses. This helps to improve the pertinence and effectiveness of interventions, and enhances the execution and quality of results in the cognitive ability enhancement process.

[0045] In this embodiment of the invention, multi-source raw data of the target object is acquired; based on the multi-source raw data using a preset cognitive efficacy model, multiple cognitive efficacy index parameters are generated by feature construction of the multi-source raw data, and weight coefficients are assigned to each index parameter to obtain a cognitive efficacy calculation dataset; the cognitive efficacy calculation dataset is weighted and calculated using the preset efficacy calculation model to obtain a comprehensive cognitive efficacy score for the target object; based on the comprehensive cognitive efficacy score, a target cognitive efficacy profile corresponding to the target object is generated; based on the target cognitive efficacy profile, a personalized intervention strategy for the target object is determined, and intervention and regulation are implemented for the target object according to the personalized intervention strategy. Through the above method, the differences in the cognitive state of the target object can be accurately characterized based on multi-dimensional data, enabling targeted dynamic intervention and improving the accuracy and effectiveness of cognitive efficacy assessment.

[0046] Optionally, in the step of obtaining multi-source raw data of the target object, periodic assessment data of the target object can be collected to obtain psychological assessment data; periodic objective behavioral data of the target object can be collected to obtain behavioral record data; periodic achievement data of the target object can be collected to obtain achievement performance data; and the psychological assessment data, behavioral record data and achievement performance data can be preprocessed to obtain multi-source raw data.

[0047] In this embodiment of the invention, the aforementioned periodic assessment data refers to quantitative records obtained from repeated psychological state assessments of the target subjects under fixed training cycles or stage nodes, used to reflect the psychological change trends of trainees at different stages. For example, during the training process, the platform organizes tests such as self-efficacy scales and self-awareness status assessments every two weeks, forming continuous time series data to determine whether the level of psychological engagement has increased or decreased. The importance of this type of data lies in the fact that it is not a one-time assessment, but rather used to track the dynamic changes in the trainees' psychological state over a long period, thereby providing a time basis for subsequent intervention and reassessment.

[0048] The aforementioned psychological assessment data can be structured numerical records reflecting psychological states, generated based on periodic psychological scales or online assessment tools. Its content typically covers multiple psychological and cognitive characteristics, such as self-efficacy, emotional stability, learning motivation, and satisfaction. For example, a self-efficacy scale can deduce a student's subjective judgment of their own abilities through scores on multiple items; cognitive engagement assessment can reflect a student's sense of importance and engagement with learning tasks.

[0049] The aforementioned periodic objective behavioral data refers to behavioral information automatically recorded by the system during the training cycle. This data characterizes students' participation and execution of learning activities, such as the number of times they attend classes, activity completion rates, attendance times and durations, and the periodicity of task submissions. This data requires no subjective feedback and is characterized by its objectivity and independence from self-reporting. For example, if a student attends a course 5 times in two weeks, compared to another student who attends only once, their participation levels will have a measurable difference.

[0050] The aforementioned behavioral record data consists of periodic objective behavioral data that has been structured and quantified for further calculation of behavioral participation intensity, stability, and behavioral fluctuation trends. For example, the behavioral records not only include the number of participations but can also generate a behavioral consistency index by statistically analyzing behavioral intervals and durations. This index reflects whether participants exhibit "periodic impulsive participation" or "continuous and stable engagement." Understandably, this data can be derived from the original system logs, and its structured representation allows behavioral characteristics to be incorporated into subsequent indicator construction and weight calculations.

[0051] The aforementioned periodic outcome data can refer to the phased learning or practical outputs formed during the training period, representing the results of the target audience's cognitive investment. Examples include course assessment scores, report ratings, work evaluations, and project task scores. It's important to note that this periodic outcome data differs from behavioral records; it does not record the behavioral process but rather the actual output resulting from the behavior. Unlike psychological assessments, it does not reflect subjective states but rather objectively represents outcomes. Therefore, this periodic outcome data can be used to determine whether a cognitive process can be transformed into actual ability or visible results.

[0052] The aforementioned performance data represents the results of periodic performance data after being graded, standardized, and quantified. For example, grades such as "Excellent," "Good," "Pass," and "Fail" are converted into numerical ranges, or the judging results are mapped to numerical forms such as contribution indices and conversion coefficients. It's important to note that performance data is used to express the quality and level of the results, not simply ranking scores. For instance, even if a student's work did not receive a high score, a significant long-term growth rate can be reflected in the performance data as demonstrating their continuous improvement, rather than a one-time achievement. This data can compensate for differences in growth trends that traditional scores cannot reflect.

[0053] In one possible embodiment, the aforementioned trainee cognitive efficacy dynamic assessment and regulation platform collects data from the target subjects according to a predetermined training cycle. Specifically, it acquires periodic assessment data of the target subjects according to fixed cycles or phased training nodes to form psychological assessment data reflecting the trainees' psychological state, such as scaled expressions of self-efficacy, self-confidence level, and cognitive engagement. Simultaneously, based on the learning system, activity system, and attendance management system, it continuously collects periodic objective behavioral data of the target subjects to form behavioral record data that can record the number of times they participate in learning, the duration of learning, the completion status of activities, and the stability of their behavior. In addition, based on information such as course grade evaluation, practical task evaluation, and achievement level classification, the platform collects periodic achievement data formed by the target subjects during the training phase, and uses this to constitute achievement performance data to reflect the trainees' cognitive execution effect and output quality.

[0054] After acquiring the data, the platform further performs preprocessing operations on the psychological assessment data, behavioral record data, and performance data, including unified formatting, noise filtering, missing data completion, numerical mapping, and scale standardization. This transforms data from different sources and with different structures into multi-source raw data that can be analyzed uniformly, providing structured data input for subsequent indicator construction and performance calculation.

[0055] Optionally, in the step of generating multiple cognitive efficacy index parameters by constructing features from multiple source raw data based on a preset cognitive efficacy model, the method further includes determining the efficacy features of each dimension in the multiple source raw data. The efficacy features are used to reflect the efficacy expression form corresponding to the raw data in different dimensions. Based on the efficacy features of each dimension, the method constructs features from the multiple source raw data to generate multiple corresponding cognitive efficacy index parameters.

[0056] In this embodiment of the invention, the aforementioned efficacy features can be feature factors extracted from multi-source raw data that can represent the role of the data in cognitive efficacy evaluation, used to distinguish the contribution direction of different data dimensions to cognitive performance. For example, in psychological data, self-efficacy and cognitive motivation can be used as efficacy features to reflect the psychological driving force of an individual's learning engagement; in behavioral data, participation frequency and behavioral stability can be used as efficacy features to express whether the executive behavior can continuously support the learning task; in outcome data, outcome level and growth trend can be used as efficacy features to reflect whether the final output can reflect the transformation effect of cognitive ability.

[0057] The aforementioned efficacy expression can be represented by numerical or hierarchical representations of different categories of raw data transformed into efficacy characteristics by the cognitive efficacy dynamic assessment and regulation platform for trainees. This quantifies trainees' cognitive abilities in corresponding dimensions. For example, emotional stability can be mapped to a stability coefficient, behavioral participation can be converted into an input ratio or consistency index, and outcome level can be expressed as a growth coefficient or contribution value. This efficacy expression allows different data to be calculated on a unified scale.

[0058] In one possible embodiment, after completing the collection and preprocessing of multi-source raw data, the above-mentioned cognitive efficacy dynamic assessment and regulation platform for trainees divides the psychological assessment data, behavioral record data and performance data into dimensions, and determines the efficacy characteristics of each dimension to reflect the performance meaning of the data in the cognitive efficacy evaluation.

[0059] Specifically, in the psychological dimension, features reflecting learning motivation, self-efficacy, and emotional stability are identified; in the behavioral dimension, features reflecting participation frequency, behavioral stability, and activity engagement are identified; and in the outcome dimension, features reflecting output level, growth trend, and achievement contribution are identified. These features are then quantified and structurally transformed. Finally, based on the identified efficacy features, features are constructed from multi-source data to generate multiple cognitive efficacy index parameters representing psychological level, behavioral engagement, and achievement ability, thus forming a set of structured indicators that can be used for subsequent calculations.

[0060] By employing the above methods and steps, psychological, behavioral, and outcome data can have a clear functional positioning and a unified scale of expression within the computational system. This allows cognitive assessment to move beyond relying on single scale results or process behaviors and instead form a more interpretable and differentiated indicator system through a structured approach based on multidimensional features, thereby improving the accuracy and stability of subsequent assessments and intervention strategy development.

[0061] Optionally, the step of assigning weight coefficients to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset further includes determining the feature distribution data corresponding to each cognitive efficacy index parameter; determining the weight coefficients corresponding to each cognitive efficacy index parameter based on the feature distribution data corresponding to each cognitive efficacy index parameter; and matching and combining each cognitive efficacy index parameter with its corresponding weight coefficient to obtain a cognitive efficacy calculation dataset.

[0062] In this embodiment of the invention, the aforementioned feature distribution data can be statistical results of cognitive efficacy index parameters in a group sample, used to reflect the contribution trend and stable performance of each index. For example, if a behavioral stability index has low dispersion in the group and a high positive correlation with outcome production, its weight can be increased in subsequent calculations; while some psychological indicators fluctuate greatly and are not easily converted into outcome performance, their weights will be reduced accordingly. Therefore, the aforementioned feature distribution data is not a single numerical value, but a statistical structure composed of mean, dispersion, trend value, and correlation.

[0063] In this embodiment, when generating the computational dataset, cognitive efficacy index parameters can be paired and bound to their corresponding weight coefficients, forming an input structure with a unified data format. For example, the behavioral stability index and its weight form a one-to-one data unit, and the psychological self-efficacy value and its weight form another data unit, ultimately constituting an indicator-weight aligned structure that can participate in the calculation. This combination method allows each indicator to participate in the calculation according to its degree of influence in subsequent weighted calculations, avoiding calculation biases caused by scale differences or unclear relationships between different indicators.

[0064] In one possible embodiment, after the aforementioned cognitive efficacy dynamic assessment and regulation platform for trainees completes the construction of multidimensional cognitive efficacy index parameters, it first performs statistical analysis on the performance of each index parameter in the current training group to form corresponding characteristic distribution data. Based on this distribution information, it assigns higher weights to indicators with high stability, obvious growth trends, or strong correlation with comprehensive efficacy performance; and assigns lower weights to indicators with large fluctuations or unstable contributions, thereby completing the determination of the corresponding weight coefficients for each cognitive efficacy index parameter.

[0065] After the weights are determined, the platform matches and combines each cognitive efficacy indicator parameter with its corresponding weight coefficient to form a cognitive efficacy calculation dataset with a unified structure. Matching and combining refers to binding the indicator value of the same learner with its corresponding weight in the group evaluation system, so that they participate in the calculation together according to a set ratio in subsequent comprehensive calculations, forming an indicator-weight aligned data input structure. The final generated calculation dataset has a unified representation and can be directly used for weighted fusion processing in subsequent efficacy calculation models.

[0066] By following the above methods and steps, different cognitive dimensions can be included in the comprehensive assessment according to their actual contributions, reducing the interference of single dimensions or unstable indicators on the overall results. This makes the comprehensive score more consistent with the actual cognitive development characteristics of the learners, which is beneficial to the accuracy and recognizability of subsequent profile presentation and personalized strategy matching.

[0067] Optionally, in the step of performing weighted calculations on the cognitive efficacy calculation dataset through a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object, the method further includes performing feature weighting and parameter fusion processing based on the values ​​of each cognitive efficacy index parameter and its corresponding weight coefficient in the cognitive efficacy calculation dataset to obtain the efficacy calculation result; and generating the comprehensive cognitive efficacy score of the target object based on the efficacy calculation result.

[0068] In this embodiment of the invention, the aforementioned feature weighting and parameter fusion processing is a computational process in which the efficacy calculation model proportionally fuses indicator parameters with their weights, so that indicators of different dimensions together constitute the overall cognitive performance according to their degree of influence. For example, when a trainee's psychological self-efficacy index value is 0.75, behavioral stability index value is 0.60, and achievement growth trend index value is 0.82, and their corresponding weights are determined to be 0.30, 0.40, and 0.30 respectively based on feature distribution statistics, a weighted fusion calculation is performed according to this ratio to obtain the efficacy calculation result: Performance calculation result = 0.75 × 0.30 + 0.60 × 0.40 + 0.82 × 0.30 = 0.713 The above performance calculation results are a single structured expression formed after weighted fusion processing. It is used to reflect the comprehensive level of the target object after integration of performance in different cognitive dimensions. It should be noted that the above performance calculation results are not the final score, but an intermediate structure used for transformation and expression. Its values ​​are convertible after fusion processing and can be used to map the comprehensive score or participate in subsequent level division, trend analysis or profile display.

[0069] In one possible embodiment, after obtaining the cognitive efficacy calculation dataset, the cognitive efficacy dynamic assessment and control platform for the trainees calls a preset efficacy calculation model to perform weighted calculations on each cognitive efficacy indicator parameter and its corresponding weight.

[0070] Based on the index values ​​and corresponding weights in the calculation dataset, feature weighting and parameter fusion processing are performed according to a unified fusion rule. The index values ​​of different dimensions are used together in the calculation according to the weight ratio to obtain the performance calculation result that represents the overall cognitive performance of the target object.

[0071] Based on the efficacy calculation results, a comprehensive cognitive efficacy score is generated for the target object. This comprehensive score serves as an overall evaluation of the target object's current cognitive efficacy level and is used for subsequent profile generation and intervention strategy matching.

[0072] By following the above methods and steps, we can avoid the misleading influence of a single indicator on the overall evaluation, make the comprehensive performance more consistent with the actual training characteristics and ability contribution structure, and improve the accuracy and comparability of cognitive performance evaluation results.

[0073] Optionally, in the step of generating a target cognitive efficacy profile corresponding to the target object based on the comprehensive cognitive efficacy score, the method further includes determining the score data corresponding to each cognitive efficacy indicator parameter based on the comprehensive cognitive efficacy score; displaying the efficacy characteristics of the current target object in a hierarchical manner based on the score data and visualizing them to generate a corresponding target cognitive efficacy profile, which is used to reflect the efficacy differences between the various dimension indicator parameters of the target object.

[0074] In this embodiment of the invention, the aforementioned score data can be standard scores generated by the cognitive efficacy dynamic assessment and control platform for trainees after converting different types of cognitive efficacy index parameters according to a unified scoring rule. These scores are used to reflect psychological, behavioral, and outcome performance on the same scale. For example, the cognitive efficacy dynamic assessment and control platform for trainees converts the self-efficacy scale into a psychological efficacy score of 0–100, the behavioral input index into a behavioral score of 0–100, and the outcome growth coefficient into an outcome score of 0–100.

[0075] The aforementioned efficacy characteristics can be the ability structure extracted from the score data by the cognitive efficacy dynamic assessment and regulation platform for the trainees, used to reflect the cognitive ability characteristics of the target object in different dimensions. For example, when the behavioral score is significantly higher than the psychological score and the achievement score, it can be identified that the object has strong behavioral execution ability but insufficient achievement transformation ability.

[0076] The aforementioned tiered display can be used by the training participants' cognitive efficacy dynamic assessment and adjustment platform to divide different dimensions of ability into several levels based on score data, such as "high level," "average performance," and "needs improvement," and assign corresponding dimensions to the corresponding levels to highlight cognitive differences. For example, a score of 82 in the psychological dimension could be classified as "high level," a score of 66 in the behavioral dimension as "average performance," and a score of 51 in the achievement dimension as "needs improvement." This tiered display can be used to determine ability priorities.

[0077] The aforementioned target cognitive efficacy profile can refer to a multi-dimensional ability structure expression formed based on score data, level differences, and efficacy characteristics, used to reflect the differences and distribution of strengths and weaknesses in the target's current cognitive efficacy across various dimensions.

[0078] In this embodiment, the aforementioned target cognitive efficacy profile can also be presented graphically, including but not limited to radar charts, bar charts, and level distribution charts, to visually demonstrate the differences in trainees' performance across psychological, behavioral, and outcome dimensions. For example, when the outcome dimension is significantly lower than the behavioral dimension, the corresponding area on the radar chart will shrink noticeably, thus visually representing the weaker abilities.

[0079] Optionally, the steps of determining personalized intervention strategies for the target object based on the target cognitive efficacy profile and implementing intervention and regulation on the target object according to the personalized intervention strategies further include: determining the target object's inferior cognitive efficacy index parameters based on the target cognitive efficacy profile; matching at least one corresponding intervention strategy in a preset strategy library based on the inferior cognitive efficacy index parameters; generating a personalized intervention strategy based on at least one corresponding intervention strategy, and implementing intervention and regulation on the target object.

[0080] In this embodiment of the invention, the aforementioned inferior cognitive efficacy index parameter can refer to an indicator that performs worse than other dimensions or is in a lower range in the cognitive efficacy profile, used to reflect the target object's shortcomings or weaknesses in the current stage. For example, when the performance score is significantly lower than the psychological and behavioral dimensions, the performance index is identified as an inferior indicator; when the behavioral stability score is low but the performance conversion is high, the behavioral execution ability is considered a weakness.

[0081] In this embodiment, the aforementioned platform for dynamic assessment and regulation of trainees' cognitive efficacy can retrieve intervention measures corresponding to the corresponding weakness dimension from a preset strategy library based on the weakness cognitive efficacy index, and align and link them according to the index type and performance deficiency. For example, for "insufficient behavioral stability," a continuous monitoring strategy can be matched; for "low self-efficacy," a psychological incentive strategy can be matched; and for "weak achievement transformation," a practice-driven or achievement-task-based strategy can be matched. More specifically, personalized training tasks can be intelligently matched and pushed from the intervention strategy library according to the calculation formula of the aforementioned target cognitive efficacy profile.

[0082] If the P-value is low: Push tasks such as "participate in a themed Party Day activity" or "pair up with a veteran Party member".

[0083] If the C value is low: Push tasks such as "organize or participate in a community cultural festival activity" or "serve as a floor leader".

[0084] If the M value is low: Push tasks such as "participate in positive psychology group counseling" and "complete a successful experience review diary".

[0085] The aforementioned personalized intervention strategies can be differentiated intervention plans generated after strategy matching is completed, based on the actual performance characteristics, current level and improvement trend of the target object, by screening, combining or adjusting the weight of multiple corresponding strategies. For example, for trainees with insufficient results transformation, different combinations of strategies with different intensities and contents may be provided for "low-input" and "low-efficiency" trainees to achieve targeted training.

[0086] In one possible embodiment, the aforementioned cognitive efficacy dynamic assessment and regulation platform for trainees can apply personalized strategies to the target group, including specific implementation forms such as task assignment, behavioral supervision, guidance and incentives, practice arrangements, and psychological counseling. It continuously records response data, behavioral changes, and performance results throughout the implementation period, providing a basis for the next reassessment, weight updates, and strategy adjustments. Specifically, the evaluation of intervention effectiveness can be calculated and verified using the following formula: Y = cX + e1 (total effect); M = aX + e2 (the effect of X on M); Y = c'X + bM + e3 (direct effects and the effect of M on Y); Where X is the independent variable, representing work score (P) or activity score (C); M is the mediating variable, representing self-efficacy score (SES); Y is the dependent variable, representing mental health score (GHQ-12) or life satisfaction score (SWLS); c, a, b, c' are regression coefficients, and e is the error term.

[0087] If coefficients a and b are significant, and the absolute value of c' is less than c or becomes insignificant, then self-efficacy (M) plays a mediating role. The cognitive efficacy dynamic assessment and regulation platform for the aforementioned trainees generates a report based on this analysis, providing decision support for managers.

[0088] like Figure 2 As shown, this embodiment of the invention also provides a dynamic assessment and regulation device 200 for trainees' cognitive efficacy, which includes: The first acquisition module 201 is used to acquire multi-source raw data of the target object; The first construction module 202 is used to generate multiple cognitive efficacy index parameters by performing feature construction on the multi-source raw data based on the multi-source raw data through a preset cognitive efficacy model, and to assign weight coefficients to each index parameter to obtain a cognitive efficacy calculation dataset. The first calculation module 203 is used to perform weighted calculation on the cognitive efficacy calculation dataset through a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object. The first generation module 204 is used to generate a cognitive efficacy profile corresponding to the target object based on the comprehensive cognitive efficacy score. The first determining module 205 is used to determine a personalized intervention strategy for the target object based on the target cognitive efficacy profile, and to perform intervention and regulation on the target object according to the personalized intervention strategy.

[0089] Optionally, the first acquisition module 201 mentioned above includes: The first acquisition submodule is used to collect periodic assessment data of the target object to obtain psychological assessment data; The second acquisition submodule is used to collect periodic objective behavioral data of the target object to obtain behavioral record data; The third acquisition submodule is used to collect periodic performance data of the target object to obtain performance data; The fourth acquisition submodule is used to preprocess the psychological assessment data, behavioral record data, and performance data to obtain multi-source raw data.

[0090] Optionally, the first building module 202 mentioned above includes: The first construction submodule is used to determine the performance characteristics of each dimension in the multi-source raw data. The performance characteristics are used to reflect the performance expression form corresponding to the raw data in different dimensions. The second construction submodule is used to construct features from the multi-source raw data based on the effectiveness features of each dimension, and generate multiple corresponding cognitive effectiveness index parameters.

[0091] Optionally, the first building module 202 mentioned above also includes: The third construction submodule is used to determine the feature distribution data corresponding to each cognitive efficacy index parameter; The fourth construction submodule is used to determine the weight coefficients corresponding to each cognitive efficacy index parameter based on the feature distribution data corresponding to each cognitive efficacy index parameter. The fifth submodule is used to match and combine the parameters of each cognitive efficacy index with their corresponding weight coefficients to obtain the cognitive efficacy calculation dataset.

[0092] Optionally, the first calculation module 203 mentioned above includes: The first calculation submodule is used to perform feature weighting and parameter fusion processing based on the values ​​of each cognitive efficacy index parameter and its corresponding weight coefficient in the cognitive efficacy calculation dataset to obtain the efficacy calculation result. The second calculation submodule is used to generate a comprehensive cognitive efficacy score for the target object based on the efficacy calculation results.

[0093] Optionally, the first generation module 204 mentioned above includes: The first generation submodule is used to determine the score data corresponding to each cognitive efficacy indicator parameter based on the comprehensive cognitive efficacy score. The second generation submodule is used to classify and display the performance characteristics of the current target object based on the score data, and to visualize them to generate a corresponding target cognitive performance profile. The cognitive performance profile is used to reflect the performance differences between the various dimension indicators of the target object.

[0094] Optionally, the first determining module 205 mentioned above includes: The first determining submodule is used to determine the disadvantaged cognitive efficacy index parameters of the target object based on the target cognitive efficacy profile; The second determining submodule is used to match at least one corresponding intervention strategy in a preset strategy library based on the disadvantage cognitive efficacy index parameters. The third determining submodule is used to generate a personalized intervention strategy based on the at least one corresponding intervention strategy, and to perform intervention and regulation on the target object.

[0095] like Figure 3 As shown, this embodiment of the invention also provides an electronic device 300, including a processor, which can execute any of the above-mentioned methods for dynamic assessment and control of cognitive efficacy of trainees.

[0096] Specifically, it includes a processor 301 and a memory 302, as well as a computer program stored in the memory 302 and capable of running on the processor 301, which implements a method for dynamically assessing and regulating the cognitive efficacy of trainees, wherein: The processor 301 runs the calculator program stored in memory 302, which describes the dynamic assessment and regulation method of trainees' cognitive efficacy, and performs the following steps: Obtain multi-source raw data of the target object; Based on the multi-source raw data, a pre-set cognitive efficacy model is used to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters, and weight coefficients are assigned to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset. By using a preset performance calculation model, the cognitive performance calculation dataset is weighted and calculated to obtain the comprehensive cognitive performance score of the target object; Based on the comprehensive cognitive efficacy score, a target cognitive efficacy profile corresponding to the target object is generated. Based on the target cognitive efficacy profile, a personalized intervention strategy is determined for the target object, and intervention and regulation are performed on the target object according to the personalized intervention strategy.

[0097] Optionally, the processor 301 performs the acquisition of multi-source raw data of the target object, including: Periodic assessment data of the target object are collected to obtain psychological assessment data; Periodic objective behavioral data of the target object are collected to obtain behavioral record data; Periodic performance data of the target object are collected to obtain performance data; The psychological assessment data, behavioral record data, and performance data are preprocessed to obtain multi-source raw data.

[0098] Optionally, the processor 301 executes the step of generating multiple cognitive efficacy index parameters by constructing features from the multi-source raw data based on the preset cognitive efficacy model, including: Determine the performance characteristics of each dimension in the multi-source raw data, wherein the performance characteristics are used to reflect the performance expression form corresponding to the raw data in different dimensions; Based on the efficacy characteristics of each dimension, feature construction is performed on the multi-source raw data to generate multiple corresponding cognitive efficacy index parameters.

[0099] Optionally, processor 301 performs the process of assigning weight coefficients to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset, including: Determine the feature distribution data corresponding to each of the cognitive efficacy index parameters; Based on the feature distribution data corresponding to each cognitive efficacy index parameter, the weight coefficients corresponding to each cognitive efficacy index parameter are determined. By matching and combining the parameters of each cognitive efficacy index with their corresponding weight coefficients, a cognitive efficacy calculation dataset is obtained.

[0100] Optionally, the processor 301 executes the weighted calculation of the cognitive efficacy calculation dataset using a preset efficacy calculation model to obtain a comprehensive cognitive efficacy score for the target object, including: Based on the values ​​of each cognitive efficacy index parameter and its corresponding weight coefficient in the cognitive efficacy calculation dataset, feature weighting and parameter fusion processing are performed to obtain the efficacy calculation result. Based on the performance calculation results, a comprehensive cognitive performance score for the target object is generated.

[0101] Optionally, the processor 301 executes the step of generating a target cognitive efficacy profile corresponding to the target object based on the comprehensive cognitive efficacy score, including: Based on the comprehensive cognitive efficacy score, determine the score data corresponding to each cognitive efficacy indicator parameter; Based on the score data, the performance characteristics of the current target object are displayed in a hierarchical manner and visualized to generate a corresponding target cognitive performance profile. The cognitive performance profile is used to reflect the performance differences between the various dimensional indicator parameters of the target object.

[0102] Optionally, the processor 301 executes the process of determining a personalized intervention strategy for the target object based on the target cognitive efficacy profile, and performs intervention and regulation on the target object according to the personalized intervention strategy, including: Based on the target cognitive efficacy profile, the negative cognitive efficacy index parameters of the target object are determined; Based on the aforementioned disadvantage cognitive efficacy index parameters, at least one corresponding intervention strategy is matched from the preset strategy library. Based on the at least one corresponding intervention strategy, a personalized intervention strategy is generated, and intervention and regulation are performed on the target object.

[0103] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the dynamic assessment and regulation method for cognitive efficacy of trainees or the application-side dynamic assessment and regulation method for cognitive efficacy of trainees provided in this invention, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0104] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be done by a computer program instructing related hardware, and can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0105] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for dynamic assessment and regulation of trainees' cognitive efficacy, characterized in that, include: Obtain multi-source raw data of the target object; Based on the multi-source raw data, a pre-set cognitive efficacy model is used to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters, and weight coefficients are assigned to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset. By using a preset performance calculation model, the cognitive performance calculation dataset is weighted and calculated to obtain the comprehensive cognitive performance score of the target object; Based on the comprehensive cognitive efficacy score, a target cognitive efficacy profile corresponding to the target object is generated. Based on the target cognitive efficacy profile, a personalized intervention strategy is determined for the target object, and intervention and regulation are performed on the target object according to the personalized intervention strategy.

2. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 1, characterized in that, The acquisition of multi-source raw data of the target object includes: Periodic assessment data of the target object are collected to obtain psychological assessment data; Periodic objective behavioral data of the target object are collected to obtain behavioral record data; Periodic performance data of the target object are collected to obtain performance data; The psychological assessment data, behavioral record data, and performance data are preprocessed to obtain multi-source raw data.

3. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 1, characterized in that, The step involves using a preset cognitive efficacy model to construct features from the multi-source raw data to generate multiple cognitive efficacy index parameters, including: Determine the performance characteristics of each dimension in the multi-source raw data, wherein the performance characteristics are used to reflect the performance expression form corresponding to the raw data in different dimensions; Based on the efficacy characteristics of each dimension, feature construction is performed on the multi-source raw data to generate multiple corresponding cognitive efficacy index parameters.

4. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 3, characterized in that, The process of assigning weight coefficients to each cognitive efficacy index parameter to obtain a cognitive efficacy calculation dataset includes: Determine the feature distribution data corresponding to each of the cognitive efficacy index parameters; Based on the feature distribution data corresponding to each cognitive efficacy index parameter, the weight coefficients corresponding to each cognitive efficacy index parameter are determined. By matching and combining the parameters of each cognitive efficacy index with their corresponding weight coefficients, a cognitive efficacy calculation dataset is obtained.

5. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 1, characterized in that, The step of performing a weighted calculation on the cognitive efficacy calculation dataset using a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object includes: Based on the values ​​of each cognitive efficacy index parameter and its corresponding weight coefficient in the cognitive efficacy calculation dataset, feature weighting and parameter fusion processing are performed to obtain the efficacy calculation result. Based on the performance calculation results, a comprehensive cognitive performance score for the target object is generated.

6. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 1, characterized in that, The step of generating a target cognitive efficacy profile for the target object based on the comprehensive cognitive efficacy score includes: Based on the comprehensive cognitive efficacy score, determine the score data corresponding to each cognitive efficacy indicator parameter; Based on the score data, the performance characteristics of the current target object are displayed in a hierarchical manner and visualized to generate a corresponding target cognitive performance profile. The cognitive performance profile is used to reflect the performance differences between the various dimensional indicator parameters of the target object.

7. The method for dynamic assessment and regulation of trainees' cognitive efficacy as described in claim 1, characterized in that, The process of determining a personalized intervention strategy for the target individual based on the target cognitive efficacy profile, and then implementing intervention and regulation on the target individual according to the personalized intervention strategy, includes: Based on the target cognitive efficacy profile, the negative cognitive efficacy index parameters of the target object are determined; Based on the aforementioned disadvantage cognitive efficacy index parameters, at least one corresponding intervention strategy is matched from the preset strategy library. Based on the at least one corresponding intervention strategy, a personalized intervention strategy is generated, and intervention and regulation are performed on the target object.

8. A device for dynamically assessing and regulating the cognitive efficacy of trainees, characterized in that, include: The first acquisition module is used to acquire multi-source raw data of the target object; The first construction module is used to generate multiple cognitive efficacy index parameters by performing feature construction on the multi-source raw data based on the multi-source raw data through a preset cognitive efficacy model, and to assign weight coefficients to each index parameter to obtain a cognitive efficacy calculation dataset. The first calculation module is used to perform weighted calculation on the cognitive efficacy calculation dataset through a preset efficacy calculation model to obtain the comprehensive cognitive efficacy score of the target object. The first generation module is used to generate a cognitive efficacy profile corresponding to the target object based on the comprehensive cognitive efficacy score. The first determining module is used to determine a personalized intervention strategy for the target object based on the target cognitive efficacy profile, and to perform intervention and regulation on the target object according to the personalized intervention strategy.

9. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the method for dynamic assessment and regulation of cognitive efficacy of trainees as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps in the method for dynamic assessment and regulation of cognitive efficacy of trainees as described in any one of claims 1 to 7.

Images