Intelligent comprehensive learning style assessment method and system for adolescents

Abstract

The present invention discloses an intelligent, all-round learning style assessment method and system for adolescents, which relates to the technical field of learning style assessment. The method is used to address the problem in existing assessment technologies of limited dimensions in adolescent learning style assessment, which leads to a lack of comprehensive understanding of learning style identification. Based on adolescents' behavioral data, physiological data, and learning record information, the method achieves a comprehensive assessment of learning style through multi-dimensional data collection and analysis. The data collection phase is divided into behavioral, physiological, and learning record areas, monitoring indicators such as interaction frequency, heart rate mean, and software usage time. The feature classification phase uses a fuzzy logic algorithm to extract cognitive, emotional, and behavioral features. The feature labeling phase calculates a comprehensive evaluation coefficient based on standard deviation and fluctuation frequency. Finally, the evaluation coefficient is combined with the preset level to screen the target object, generate personalized assessment results, and achieve precise intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of learning style assessment, and more specifically, to an intelligent all-round learning style assessment method and system for adolescents. Background Art

[0002] With the continuous improvement of educational informatization and intelligence, the identification and intervention of the learning status and personality characteristics of young people are becoming an increasingly important foundation for personalized teaching and teaching students in accordance with their aptitude. Currently, common methods for assessing adolescent learning styles mainly rely on questionnaires, static assessment scales, or subjective observations by teachers. These methods suffer from problems such as a single assessment dimension, insufficient ability to identify dynamic changes, and a lagging personalized intervention mechanism.

[0003] On the other hand, during the actual learning process, adolescents' multidimensional data, such as their behavioral performance, physiological reactions, and learning records, possess potential correlations and quantifiable characteristics. Through data collection and intelligent modeling, dynamic tracking and quantitative assessment of their cognitive abilities, emotional states, and behavioral habits can be achieved. Currently, there is a lack of a method and system for assessing adolescent learning styles based on multimodal data fusion and intelligent feature recognition that can achieve comprehensive feature recognition, dynamic assessment, and graded adjustments to accommodate individual differences and stage-specific developmental characteristics.

[0004] The existing technology has the following deficiencies:

[0005] At present, the existing assessment technologies for adolescent learning styles have limited assessment dimensions, static evaluation methods, and insufficient personalized responses, resulting in a lack of comprehensiveness in the identification of learning styles, difficulty in capturing changes in adolescent status in real time, and an inability to generate accurate personalized intervention strategies based on the assessment results. Therefore, an intelligent, comprehensive adolescent learning style assessment method and system is proposed.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent method and system for all-round learning style assessment of adolescents, which solves the problems raised in the above-mentioned background technology by utilizing multimodal data fusion, feature intelligent classification modeling and personalized dynamic intervention mechanism.

[0008] To achieve the above objectives, the present invention provides the following technical solutions: an intelligent all-round learning style assessment method and system for adolescents, comprising the following steps:

[0009] Step S1: Divide multiple data collection areas according to the data distribution in the learning environment and perform screening to preliminarily collect the behavioral data and physiological data of the adolescents to obtain the adolescents' learning record information;

[0010] Step S2: Classify the characteristics of adolescents by integrating their behavioral data, physiological data, and learning record information, and extract cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics;

[0011] Step S3: Mark the different characteristics of the adolescent based on the feature classification results, collect the change amplitude and frequency of all the marked characteristics of the adolescent, calculate the comprehensive evaluation coefficient, and determine whether the adolescent needs personalized adjustment. Set the personalized adjustment level based on the cognitive ability characteristics and the comprehensive evaluation coefficient;

[0012] Step S4: Screen out adolescents who need personalized adjustment, set the adjustment order according to the personalized adjustment level of the screened adolescents, and generate the final evaluation results based on the adjustment order.

[0013] In a preferred embodiment, the data collection area is divided into a behavioral data collection area, a physiological data collection area, and a learning record collection area according to the data distribution in the learning environment, and the corresponding data in the collection area is screened;

[0014] Behavioral data includes interaction frequency, physiological data includes heart rate data average, and learning record information includes software usage time, number of completed tasks, assessment scores, and learning content concentration.

[0015] In a preferred embodiment, in the behavior data collection area, the total number of interaction events is accumulated, and the total number is divided by the duration of the data collection window to generate the interaction frequency;

[0016] In the physiological data collection area, the current heart rate data is obtained in real time and statistics are performed, and the average of all heart rate data in the data collection window is taken;

[0017] In the learning record collection area, when teenagers open or close the learning software, the current timestamp is automatically recorded, and the usage time of the learning software within the time window is accumulated and calculated; when teenagers complete a task, it is marked as task completed, and the number of tasks completed within the time window is counted; when teenagers submit the evaluation results, their evaluation scores are recorded, and the average evaluation scores within the time window are taken to obtain the evaluation score; the knowledge points of each learning content are divided into various labels, and after the learning time of the same label is counted, the statistical results are compared with the total learning time to obtain the concentration of learning content.

[0018] In a preferred embodiment, the behavioral data, physiological data, and learning record information are subjected to feature classification, which is classified into cognitive ability features, emotional state features, and behavioral habit features;

[0019] Cognitive ability characteristics include software usage time and the number of completed tasks, emotional state characteristics include interaction frequency and heart rate data average, behavioral habit characteristics include assessment scores and learning content concentration. By setting fuzzy rules, the combination of each feature is mapped to the classification level of each feature. Fuzzy reasoning is performed according to the fuzzy rules to determine the level of each feature and obtain the precise value of each feature.

[0020] In a preferred embodiment, the precise values ​​of adolescent cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics are marked, a fixed time window is set, and the standard deviation is used to calculate the variation range of the precise value of each characteristic. At the same time, the ratio of the number of times each characteristic fluctuates to the total number of sampling times is used as the frequency of change of the precise value of each characteristic.

[0021] In a preferred embodiment, after obtaining the change amplitude and change frequency of each feature, performing normalization processing, and then obtaining the comprehensive evaluation coefficient of each feature by weighted summation, the comprehensive evaluation coefficient of each feature is normalized to obtain the comprehensive evaluation coefficient;

[0022] Compare the comprehensive evaluation coefficient with the preset threshold. If the comprehensive evaluation coefficient is greater than or equal to the preset threshold, it is judged that the adolescent needs personalized adjustment. If the comprehensive evaluation coefficient is less than the preset threshold, it is judged that the adolescent does not need personalized adjustment.

[0023] In a preferred embodiment, comprehensive evaluation coefficients greater than or equal to a preset threshold are screened out, and the corresponding adolescents are marked as adolescents who need personalized adjustment, and the personalized adjustment level is set based on the precise value of each adolescent's cognitive ability characteristics and the comprehensive evaluation coefficient.

[0024] In a preferred embodiment, adolescents marked as requiring personalized adjustment are screened, sorted in order according to the adjustment level and the standardized value of the comprehensive evaluation coefficient, and the adjustment order is set;

[0025] According to the adjustment order, sort from large to small to obtain the final adjustment order list and generate the final evaluation results.

[0026] The intelligent comprehensive learning style assessment system for adolescents includes a data collection module, a feature classification module, a level assessment module, and a personality adjustment module. The functions of each module are as follows:

[0027] The data collection module divides the data into multiple collection areas according to the data distribution in the learning environment and performs screening, and performs preliminary collection of the adolescents' behavioral data and physiological data to obtain the adolescents' learning record information;

[0028] The feature classification module integrates the adolescents' behavioral data, physiological data, and learning record information to classify the adolescents' features and extract cognitive ability features, emotional state features, and behavioral habit features;

[0029] The level assessment module labels the different characteristics of adolescents based on the feature classification results, collects the change amplitude and frequency of all the marked characteristics of adolescents, calculates the comprehensive assessment coefficient, and determines whether the adolescents need personalized adjustment. The personalized adjustment level is set based on the cognitive ability characteristics and the comprehensive assessment coefficient.

[0030] The personality adjustment module selects adolescents who need personalized adjustment, sets the adjustment order according to the personalized adjustment level of the adolescents after screening, and generates the final evaluation results according to the adjustment order.

[0031] Technical effects and advantages of the present invention:

[0032] The present invention achieves a comprehensive assessment of adolescent learning styles through multi-dimensional data collection and analysis based on adolescent behavioral data, physiological data and learning record information. In the data collection stage, the learning environment is divided into behavioral data collection area, physiological data collection area and learning record collection area, and the interaction frequency, heart rate data mean, software usage time, number of tasks completed, assessment score and learning content concentration are monitored and counted. In the feature classification stage, fuzzy reasoning and defuzzification processing are performed on each data through fuzzy logic algorithm, and then cognitive ability characteristics, emotional state characteristics and behavioral habit characteristics are extracted. In the feature labeling stage, the change amplitude and change frequency are calculated by the standard deviation and the proportion of the number of fluctuations of each feature to the total number of sampling times, and the comprehensive evaluation coefficient is calculated by combining the change amplitude and change frequency. According to the cognitive ability characteristics and the comprehensive evaluation coefficient combined with the preset level classification standards, adolescents who need adjustment are screened, and personalized evaluation results are generated according to the adjustment level and priority to ensure that learning intervention is accurate and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of the method for intelligent all-round learning style assessment of adolescents according to the present invention.

[0034] Figure 2 This is the fuzzy logic reasoning diagram of the intelligent all-round learning style assessment method for teenagers of the present invention.

[0035] Figure 3 This is a module diagram of the intelligent all-round learning style assessment system for teenagers of the present invention. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] Example 1: Please refer to Figure 1 and Figure 2 , the intelligent all-round learning style assessment method for adolescents, the specific operation process is as follows:

[0038] Step S1: Divide multiple data collection areas according to the data distribution in the learning environment and perform screening to preliminarily collect the behavioral data and physiological data of the adolescents to obtain the adolescents' learning record information;

[0039] Step S2: Classify the characteristics of adolescents by integrating their behavioral data, physiological data, and learning record information, and extract cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics;

[0040] Step S3: Mark the different characteristics of the adolescent based on the feature classification results, collect the change amplitude and frequency of all the marked characteristics of the adolescent, calculate the comprehensive evaluation coefficient, and determine whether the adolescent needs personalized adjustment. Set the personalized adjustment level based on the cognitive ability characteristics and the comprehensive evaluation coefficient;

[0041] Step S4: Screen out adolescents who need personalized adjustment, set the adjustment order according to the personalized adjustment level of the screened adolescents, and generate the final evaluation results based on the adjustment order.

[0042] The specific implementation is as follows:

[0043] In step S1, based on the data distribution in the learning environment, the data collection area is divided into a behavioral data collection area, a physiological data collection area, and a learning record collection area. The behavioral data collection area is used to monitor the adolescent's interactive behavior in the learning software to obtain data on the frequency of their operation during the learning process; the physiological data collection area is used to monitor the adolescent's physiological state data through wearable devices to reflect their physiological reactions during the learning process; and the learning record collection area is used to collect the adolescent's learning activity data in the learning software to quantify their task completion and learning concentration.

[0044] On the basis of the above-mentioned regional division, the data of each collection area is screened and specific data is collected.

[0045] In the behavioral data collection area, the interactive behaviors of teenagers during the learning process are monitored. Interactive behaviors refer to the clicks, slides, and input operations of teenagers in the learning software interface. The data collection window is set to n minutes. In each data collection window, all interactive events of teenagers in the learning software are monitored, and the total number of interactive events is accumulated. The total number is divided by the duration of the data collection window to generate the interaction frequency, and the interaction frequency is used as the behavioral data. The calculation formula is: , where F is the interaction frequency, C is the total number of interaction events in the data collection window, and T is the total duration of the data collection window in seconds. The calculation formula is .

[0046] In the physiological data collection area, heart rate data is collected in real time through wearable devices. To ensure data consistency, a data collection window of e minutes is also used, and the unit time is set to m seconds. The current heart rate data is obtained in real time and statistically analyzed. The mean of all heart rate data in the data collection window is taken as the physiological data. The specific calculation formula is: ,in, is the mean of all heart rate data, k is the total number of heart rate data samples in the data acquisition window, and the calculation formula is , is the heart rate data collected for the hth time.

[0047] In the learning record collection area, by monitoring the learning activity data of teenagers in the learning software, we can obtain their software usage time, number of completed tasks, assessment scores and concentration of learning content, and use the above parameters as learning record information. The time window of the learning record collection area is set to 24 hours.

[0048] Software usage time refers to the total time that teenagers use learning software within the time window. The foreground activity status of the learning software is monitored. Whenever a teenager opens or closes the learning software, the current timestamp is automatically recorded and the usage time of the learning software within the time window is accumulated and calculated.

[0049] The number of completed tasks refers to the total number of tasks completed by adolescents within the time window. The task interface in the learning software is monitored. Whenever a teenager completes a task and clicks the "Done" button, it is marked as task completed, and the number of completed tasks within the time window is counted.

[0050] The assessment score refers to the average score of the adolescents in the assessment within the time window. The assessment interface in the learning software is monitored. Whenever the adolescent submits the assessment result, his / her assessment score is recorded, and the average score within the time window is taken.

[0051] The concentration of learning content refers to the proportion of time that teenagers spend studying the same knowledge point within the time window. Based on the knowledge point labels of the content that teenagers learn within the time window, the learning time of the same knowledge point is counted, and the ratio of the learning time of the same knowledge point to the total learning time is defined as the concentration of learning content. The learning time of the same knowledge point is calculated by taking the knowledge point with the longest learning time within the time window. The calculation formula is: , where Q is the concentration of learning content, The learning time for the same knowledge point, is the total learning time, that is, the length of time the software is used.

[0052] It should be noted that the task interface is the user interface in the learning software used to assign, display and guide learning tasks, and the evaluation interface is the user interface in the learning software used to evaluate user learning outcomes and provide feedback on learning effects. They will not be discussed in detail here.

[0053] In step S2, the adolescents' behavioral data, physiological data and learning record information are integrated to perform feature classification and feature extraction on the adolescents. Specifically, the features are divided into cognitive ability features, emotional state features and behavioral habit features. Each feature is divided into three levels: primary, secondary and tertiary based on the fuzzy logic algorithm, and a corresponding fuzzy rule table is established. The precise value of each feature is calculated through fuzzy reasoning and defuzzification process.

[0054] For cognitive ability characteristics, the input data includes the software usage time and the number of completed tasks in the learning record information. The software usage time is defined as short according to 0-30 minutes, medium according to 30-60 minutes, and long according to more than 60 minutes; the number of completed tasks is defined as low according to 0-5, medium according to 5-15, and high according to more than 15. Fuzzy rules map the combination of software usage time and the number of completed tasks to three levels of cognitive ability characteristics. For example, when the software usage time is short and the number of completed tasks is low, the cognitive ability characteristic is low; when the software usage time is medium and the number of completed tasks is high, the cognitive ability characteristic is high. Fuzzy reasoning is performed according to fuzzy rules to determine the level of cognitive ability characteristics. During the reasoning process, the membership degree of each combination is calculated and defuzzified by combining the center of gravity method to finally obtain the precise value of the cognitive ability characteristic.

[0055] For example, the input data software usage time equal to 45 minutes and the number of completed tasks equal to 8 are mapped to each fuzzy set, and their membership is calculated. The center of gravity method is used to calculate the exact value of the cognitive ability feature, and the result is , the exact value of the output cognitive ability feature obtained by comparing the central value of the fuzzy set is close to the high interval.

[0056] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this example uses three fuzzy sets as an example, the software usage time and the number of completed tasks can actually be divided into more than three sets to facilitate better precise adjustment based on different values. This will not be elaborated here.

[0057] The input data for emotional state features includes interaction frequency from behavioral data and mean heart rate from physiological data. Interaction frequency is categorized as 0-10 beats / minute (low), 10-30 beats / minute (medium), and 30 beats / minute or higher (high). Heart rate is categorized as 50-70 beats / minute (low), 70-100 beats / minute (normal), and 100 beats / minute or higher (high). Fuzzy rules combine interaction frequency and heart rate to infer emotional state. For example, when interaction frequency and heart rate are both high, the emotional state is characterized by tension (Level 1); when interaction frequency and heart rate are both low, the emotional state is characterized by fatigue (Level 3). During the inference process, the degree of membership for each combination is calculated using the same fuzzy inference rules, and the precise value of the emotional state feature is then calculated using the center of gravity method. The detailed inference process is described above.

[0058] Behavioral habit characteristics are calculated based on assessment scores and learning content concentration. Assessment scores are categorized as 0-60 (low), 60-80 (medium), and 80-100 (high); concentration is categorized as 0-0.4 (low), 0.4-0.7 (medium), and 0.7-1.0 (high). Fuzzy rules map the combination of assessment scores and learning content concentration into three levels of behavioral habit characteristics. For example, a low assessment score and low learning content concentration indicate a poor behavioral habit characteristic; a high assessment score and high learning content concentration indicate a good behavioral habit characteristic. Through a fuzzy inference process, combined with defuzzification using the centroid method, the precise value of the behavioral habit characteristic is ultimately obtained.

[0059] In step S3, by marking the precise values ​​of the adolescents' cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics, the change amplitude and change frequency of the precise values ​​of each characteristic are collected, and the comprehensive evaluation coefficient is calculated based on this. The personalized adjustment level is determined based on the cognitive ability characteristics and the comprehensive evaluation coefficient. Each characteristic is marked, and a fixed time window of 24 hours is set, with a unit time of 1 hour, a total of 24 sampling points, and the change amplitude and change frequency of the precise values ​​of each characteristic are recorded. The change amplitude is calculated using the standard deviation Calculation, the formula is ,in, represents the value of the i-th feature at the j-th sampling point, It represents the average value of the feature in the current fixed time window, and n represents the number of sampling points. At the same time, the ratio of the number of times each feature fluctuates to the total number of sampling times is defined as the change frequency , and its calculation formula is For example, if the cognitive ability characteristic fluctuates 4 times in 18 sampling points, then its change frequency f is .

[0060] After obtaining the change range and change frequency of the exact value of each feature, normalize them and then calculate the comprehensive evaluation coefficient by weighted summation. The comprehensive evaluation coefficient is calculated by weighted summation of the standardized results of the change range and change frequency of the exact value of each feature. The calculation formula is: ,in, is the comprehensive evaluation coefficient, and are the weight coefficients of the change amplitude and change frequency of the exact value of each feature, and i is the index of each feature;

[0061] The comprehensive evaluation coefficient is standardized so that its value is limited to the interval [0,1]. The calculation formula is: ,in, is the minimum value in the sample, is the maximum value in the sample, is the comprehensive evaluation coefficient after standardization.

[0062] Compare the comprehensive evaluation coefficient with the preset threshold. If the comprehensive evaluation coefficient is greater than or equal to the preset threshold, it is judged that the adolescent needs personalized adjustment. If the comprehensive evaluation coefficient is less than the preset threshold, it is judged that the adolescent does not need personalized adjustment.

[0063] It should be noted that the above-mentioned preset thresholds are obtained through experimental calculations by professionals in this field and will not be elaborated here.

[0064] Adolescents with comprehensive assessment coefficients greater than or equal to a preset threshold are screened and marked as requiring personalized adjustments. The personalized adjustment level is then determined based on the precise values ​​of each adolescent's cognitive ability profile and the comprehensive assessment coefficient. To ensure a consistent comparison and calculation, the precise values ​​of the cognitive ability profiles are first standardized.

[0065] Adjustment level Cognitive ability characteristics Comprehensive evaluation coefficient Mandatory adjustment (level 1) 0.81 - 1.00 0.76 - 1.00 Heavy Adjustment (Level 2) 0.61 - 0.80 0.51 - 0.75 Moderate adjustment (level 3) 0.31 - 0.60 0.26 - 0.50 Slight adjustment (level 4) 0.00 - 0.30 0.00 - 0.25

[0066] According to the above grading criteria, if the cognitive ability characteristics and comprehensive assessment coefficients fall into different ranges, the higher level will be prioritized as the final personalized adjustment level. For example, if a teenager's cognitive ability characteristic value is 0.72, corresponding to severe adjustment, and their comprehensive assessment coefficient is 0.44, corresponding to moderate adjustment, the final adjustment level will be severe adjustment.

[0067] In step S4, the adolescents marked as needing personalized adjustment are screened out, sorted according to the adjustment level and comprehensive evaluation coefficient, and the adjustment order is set. The adjustment order calculation formula is: ,in, is the adjustment order of adolescents, L is the adjustment level weight (forced adjustment = 3, moderate adjustment = 2, slight adjustment = 1), and C is the comprehensive evaluation coefficient after standardized processing of adolescents.

[0068] For example, if an adolescent's adjustment level is moderate adjustment (weight = 2) and its comprehensive assessment coefficient is 0.65, its adjustment order is calculated as .

[0069] Sort by P value from large to small to obtain the final adjustment order list and generate the final evaluation results to ensure that high-risk individuals are given priority, achieve more accurate personalized adjustment level determination and intervention strategy formulation, reduce the risk of abnormal fluctuations in adolescent behavior and optimize adolescent learning performance.

[0070] Example 2: Please refer to Figure 3 The intelligent all-round learning style assessment system for teenagers includes a method for implementing intelligent all-round learning style assessment for teenagers, including a data collection module, a feature classification module, a level assessment module, and a personality adjustment module. The functions of each module are as follows:

[0071] The data collection module divides the data into multiple collection areas according to the data distribution in the learning environment and performs screening, and performs preliminary collection of the adolescents' behavioral data and physiological data to obtain the adolescents' learning record information;

[0072] The feature classification module integrates the adolescents' behavioral data, physiological data, and learning record information to classify the adolescents' features and extract cognitive ability features, emotional state features, and behavioral habit features;

[0073] The level assessment module labels the different characteristics of adolescents based on the feature classification results, collects the change amplitude and frequency of all the marked characteristics of adolescents, calculates the comprehensive assessment coefficient, and determines whether the adolescents need personalized adjustment. The personalized adjustment level is set based on the cognitive ability characteristics and the comprehensive assessment coefficient.

[0074] The personality adjustment module selects adolescents who need personalized adjustment, sets the adjustment order according to the personalized adjustment level of the adolescents after screening, and generates the final evaluation results according to the adjustment order.

[0075] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0077] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0078] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0079] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0080] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0081] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0083] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0085] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0086] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An intelligent, all-round learning style assessment method for adolescents, characterized by: The following steps are involved: Step S1: Divide multiple data collection areas according to the data distribution in the learning environment and perform screening to preliminarily collect the behavioral data and physiological data of the adolescents to obtain the adolescents' learning record information; Step S2: Classify the characteristics of adolescents by integrating their behavioral data, physiological data, and learning record information, and extract cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics; Step S3: Mark the different characteristics of the adolescent based on the feature classification results, collect the change amplitude and frequency of all the marked characteristics of the adolescent, calculate the comprehensive evaluation coefficient, and determine whether the adolescent needs personalized adjustment. Set the personalized adjustment level based on the cognitive ability characteristics and the comprehensive evaluation coefficient; By marking the precise values ​​of adolescents' cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics, the change amplitude and frequency of the precise values ​​of each characteristic are collected, and a comprehensive evaluation coefficient is calculated based on this. The personalized adjustment level is determined based on the cognitive ability characteristics and the comprehensive evaluation coefficient. Each characteristic is marked, and a fixed time window of 24 hours is set, with a unit time of 1 hour, for a total of 24 sampling points. The change amplitude and frequency of the precise value of each characteristic are recorded; Standard deviation Calculation, the formula is , in, represents the value of the i-th feature at the j-th sampling point, It represents the average value of the feature in the current fixed time window, n represents the number of sampling points, and the ratio of the number of fluctuations of each feature to the total number of sampling times is defined as the change frequency , and its calculation formula is ; After obtaining the change amplitude and change frequency of the exact value of each feature, after standardization, the comprehensive evaluation coefficient is obtained by weighted summation. The comprehensive evaluation coefficient is obtained by weighted summation of the standardized results of the change amplitude and change frequency of the exact value of each feature. The calculation formula is ,in, is the comprehensive evaluation coefficient, and are the weight coefficients of the change amplitude and change frequency of the exact value of each feature; Comparing the comprehensive evaluation coefficient with a preset threshold value, if the comprehensive evaluation coefficient is greater than or equal to the preset threshold value, it is determined that the adolescent needs personalized adjustment; if the comprehensive evaluation coefficient is less than the preset threshold value, it is determined that the adolescent does not need personalized adjustment; Step S4: Screening out adolescents who need personalized adjustment, setting an adjustment order based on the personalized adjustment levels of the screened adolescents, and generating a final assessment result based on the adjustment order; Screen out the adolescents who are marked as needing personalized adjustment, sort them according to the adjustment level and comprehensive evaluation coefficient, and set the adjustment order. The adjustment order calculation formula is: , where P is the adjustment order of adolescents and L is the adjustment level weight. is the comprehensive evaluation coefficient of adolescents; sort by P value from large to small to obtain the final adjusted order list and generate the final evaluation results.

2. The intelligent all-round learning style assessment method for adolescents according to claim 1 is characterized by: According to the data distribution in the learning environment, the data collection area is divided into behavioral data collection area, physiological data collection area and learning record collection area, and the corresponding data in the collection area is screened; Behavioral data includes interaction frequency, physiological data includes heart rate data average, and learning record information includes software usage time, number of completed tasks, assessment scores, and learning content concentration.

3. The intelligent all-round learning style assessment method for adolescents according to claim 2 is characterized by: In the behavioral data collection area, the total number of interaction events is accumulated and divided by the duration of the data collection window to generate the interaction frequency; In the physiological data collection area, the current heart rate data is obtained in real time and statistics are performed, and the average of all heart rate data in the data collection window is taken; In the learning record collection area, when teenagers open or close the learning software, the current timestamp is automatically recorded, and the usage time of the learning software within the time window is accumulated and calculated; when teenagers complete a task, it is marked as task completed, and the number of tasks completed within the time window is counted; when teenagers submit the evaluation results, their evaluation scores are recorded, and the average evaluation scores within the time window are taken to obtain the evaluation score; the knowledge points of each learning content are divided into various labels, and after the learning time of the same label is counted, the statistical results are compared with the total learning time to obtain the concentration of learning content.

4. The intelligent all-round learning style assessment method for adolescents according to claim 2 is characterized by: Classify behavioral data, physiological data, and learning record information into cognitive ability characteristics, emotional state characteristics, and behavioral habit characteristics; Cognitive ability characteristics include software usage time and the number of completed tasks, emotional state characteristics include interaction frequency and heart rate data average, behavioral habit characteristics include assessment scores and learning content concentration. By setting fuzzy rules, the combination of each feature is mapped to the classification level of each feature. Fuzzy reasoning is performed according to the fuzzy rules to determine the level of each feature and obtain the precise value of each feature.

5. An intelligent youth comprehensive learning style assessment system, used to implement the intelligent youth comprehensive learning style assessment method according to any one of claims 1 to 4, characterized in that: It includes data collection module, feature classification module, grade assessment module and personality adjustment module. The functions of each module are as follows: The data collection module divides the data into multiple collection areas according to the data distribution in the learning environment and performs screening, and performs preliminary collection of the adolescents' behavioral data and physiological data to obtain the adolescents' learning record information; The feature classification module integrates the adolescents' behavioral data, physiological data, and learning record information to classify the adolescents' features and extract cognitive ability features, emotional state features, and behavioral habit features; The level assessment module labels the different characteristics of adolescents based on the feature classification results, collects the change amplitude and frequency of all the marked characteristics of adolescents, calculates the comprehensive assessment coefficient, and determines whether the adolescents need personalized adjustment. The personalized adjustment level is set based on the cognitive ability characteristics and the comprehensive assessment coefficient. The personality adjustment module selects adolescents who need personalized adjustment, sets the adjustment order according to the personalized adjustment level of the adolescents after screening, and generates the final evaluation results according to the adjustment order.

Images