CN116167499A - Prediction result acquisition method, equipment and medium based on multi-path index system - Google Patents
Prediction result acquisition method, equipment and medium based on multi-path index systemDownload PDFInfo
- Publication number
- CN116167499A CN116167499ACN202211690722.5ACN202211690722ACN116167499ACN 116167499 ACN116167499 ACN 116167499ACN 202211690722 ACN202211690722 ACN 202211690722ACN 116167499 ACN116167499 ACN 116167499A
- Authority
- CN
- China
- Prior art keywords
- classroom
- performance
- indicators
- prediction model
- grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及深度学习技术领域，尤其是涉及一种基于多路指标体系的预测成绩获取方法、设备、介质。The present invention relates to the technical field of deep learning, in particular to a method, device and medium for obtaining prediction results based on a multi-way index system.
背景技术Background technique
近年来，在线学生成绩预测已经成为教育数据挖掘领域的热门话题之一，吸引了大量研究人员和学者的兴趣。目前，该领域已经提出了很多优秀的算法，并且大多80％的准确率。如今在线学习数据激增，进而导致不同的学习行为和属性对学生期末表现的潜在影响是否存在波动成为了新的问题，并且教师不清楚原有的关注点和结论是否可复用以指导学生。In recent years, online student performance prediction has become one of the hot topics in the field of educational data mining, attracting the interest of a large number of researchers and scholars. At present, many excellent algorithms have been proposed in this field, and most of them have an accuracy rate of 80%. Nowadays, online learning data is proliferating, which leads to new problems whether the potential impact of different learning behaviors and attributes on students' final performance fluctuates, and teachers do not know whether the original concerns and conclusions can be reused to guide students.
教育数据挖掘是数据挖掘中的一项重要应用，也是近几年逐渐热门的话题，旨在使用数据挖掘来分析学生各种行为，促进教育环境中的发现，以改善学习和教学环境。通常，从分析方法、学业成果预测、行为预测、留存率预测四个方面来展开研究。目前，学生成绩在高校往往被认为最能反映学生学习成果的表现之一，因此预测学生成绩成为该领域中重要的研究方向。通常，学生在线学习情况等教育数据通常作为学生在线学习行为指标放入模型以预测学生期末表现。Educational data mining is an important application in data mining, and it is also a hot topic in recent years. It aims to use data mining to analyze various behaviors of students, promote discoveries in the educational environment, and improve the learning and teaching environment. Usually, research is carried out from four aspects: analysis methods, academic achievement prediction, behavior prediction, and retention rate prediction. At present, student performance in colleges and universities is often considered to be one of the performances that best reflect students' learning outcomes, so predicting student performance has become an important research direction in this field. Usually, educational data such as students' online learning situation is usually put into the model as an indicator of students' online learning behavior to predict students' end-of-semester performance.
在线自主学习需要学生同学在线学习资源进行学习和测试，线上直播课堂为教师和学生通过在线直播授课的形式代替以往面对面授线下课堂讲学。在这种形式下，学生的混合学习行为表现为学习行为指标与线上课堂指标的组合形式。然而，这与原有的在线学习行为指标是不同的，学生混合学习行为不仅包含在线学习行为指标(比如视频观看量、点击量等)，还包括线上直播课堂中与教师互动、课堂态度等多种线上课堂学习行为指标。Online self-directed learning requires students and classmates to study and test online learning resources. Online live classrooms replace face-to-face offline classroom lectures for teachers and students through online live lectures. In this form, students' blended learning behavior is manifested as a combination of learning behavior indicators and online classroom indicators. However, this is different from the original online learning behavior indicators. The mixed learning behavior of students not only includes online learning behavior indicators (such as video viewing, clicks, etc.), but also includes interaction with teachers in online live classrooms, classroom attitudes, etc. A variety of online classroom learning behavior indicators.
综上，当前缺少一种在翻转课堂下学生成绩预测的多路指标体系，以解决或部分解决教学形式的改变使得学生成绩影响因素变化，从而导致学生成绩预测准确度较低的问题。To sum up, there is currently a lack of a multi-channel index system for student performance prediction in flipped classrooms, to solve or partially solve the problem that the change of teaching form makes the factors affecting student performance change, which leads to the problem of low accuracy of student performance prediction.
发明内容Contents of the invention
本发明的目的就是为了克服上述现有技术存在的缺陷而提供一种基于多路指标体系的预测成绩获取方法、设备、介质，以解决或部分解决学生成绩影响因素变化导致学生成绩预测准确度较低的问题。The purpose of the present invention is to provide a method, device and medium for obtaining predicted grades based on a multi-way index system in order to overcome the above-mentioned defects in the prior art, so as to solve or partially solve the problem that the students' grades are predicted to be less accurate due to changes in factors affecting student grades. low problem.
本发明的目的可以通过以下技术方案来实现：The purpose of the present invention can be achieved through the following technical solutions:
本发明的一个方面，提供了一种基于多路指标体系的预测成绩获取方法，包括如下步骤：One aspect of the present invention provides a method for obtaining predicted performance based on a multi-way index system, comprising the following steps:
获取一段时间内的学习行为指标，输入到预训练好的成绩预测模型中，获取成绩等级预测结果，Obtain the learning behavior indicators for a period of time, input them into the pre-trained grade prediction model, and obtain the grade prediction results,
其中，所述的预训练好的成绩预测模型的获取包括如下步骤：Wherein, the acquisition of the pre-trained performance prediction model includes the following steps:
获取包括多路指标体系的训练样本集，其中，所述训练样本集中的每个样本均包括行为指标和对应的实际成绩等级，所述的行为指标包括课堂表现评价指标、学生课堂主观感受评价指标和学生课堂态度评价指标；Obtain a training sample set including a multi-way index system, wherein each sample in the training sample set includes a behavior index and a corresponding actual grade of achievement, and the behavior index includes a classroom performance evaluation index, and a student's classroom subjective feeling evaluation index and students' classroom attitude evaluation indicators;
基于所述训练样本集对所述成绩预测模型进行训练，损失函数值达到预设收敛条件后，获得所述预训练好的成绩预测模型。The performance prediction model is trained based on the training sample set, and the pre-trained performance prediction model is obtained after a loss function value reaches a preset convergence condition.
作为优选的技术方案，基于所述训练样本集对所述成绩预测模型进行训练，损失函数值达到预设收敛条件后，获得所述预训练好的成绩预测模型具体为：As a preferred technical solution, the performance prediction model is trained based on the training sample set, and after the loss function value reaches the preset convergence condition, the pre-trained performance prediction model is obtained specifically as follows:
将所述训练样本集按照预设比例划分为训练集和测试集；Dividing the training sample set into a training set and a test set according to a preset ratio;
使用所述训练集对所述成绩预测模型进行训练，训练后用所述测试集对所述成绩预测模型进行验证，判断损失函数值是否达到预设收敛条件，若否，重复执行本步骤，若是，获得所述预训练好的成绩预测模型。Use the training set to train the performance prediction model, use the test set to verify the performance prediction model after training, and judge whether the loss function value reaches the preset convergence condition, if not, repeat this step, if so , to obtain the pre-trained performance prediction model.
作为优选的技术方案，所述的训练样本集的获取包括如下步骤：As a preferred technical solution, the acquisition of the training sample set includes the following steps:
获取包含多路特征的行为数据，根据所述行为数据，得到组合特征，根据所述组合特征获取行为指标，获取包括所述行为指标与对应的实际成绩等级的所述训练样本集。Acquiring behavior data containing multiple features, obtaining combined features based on the behavior data, acquiring behavior indicators according to the combined features, and acquiring the training sample set including the behavior indicators and corresponding actual performance levels.
作为优选的技术方案，根据所述组合特征获取行为指标具体为：As a preferred technical solution, the behavioral indicators obtained according to the combined features are specifically:
去除不正常的样本后，根据所述包含多路特征的行为数据，通过主成分分析获取所述组合特征。After removing abnormal samples, the combined features are obtained through principal component analysis according to the behavior data containing multi-channel features.
作为优选的技术方案，所述的课堂表现评价指标包括以下指标中的一个或多个：学生举手次数、学生回答次数、教师对学生回答的有效性判定；所述学生课堂主观感受评价指标包括如下指标中的一个或多个：课堂内容的理解程度、教师所布置任务的难易程度评分、学生对课程教师的评分、同学对自己的课堂听课影响、手机对自己的课堂影响；所述的学生课堂态度评价指标包括如下指标中的一个或多个：线上课堂签到率、课程项目参与度和积极度，所述的行为指标还包括在线学习行为指标，所述的在线学习行为指标包括以下指标中的一个或多个：视频观看量、视频观看时长、任务点完成率、总点击量、章节测验完成率、章节测验得分、小组评分。As a preferred technical solution, the classroom performance evaluation indicators include one or more of the following indicators: the number of times students raise their hands, the number of times students answer, and the teacher's judgment on the validity of students' answers; the evaluation indicators of the students' subjective feelings in the classroom include One or more of the following indicators: the degree of understanding of classroom content, the degree of difficulty of tasks assigned by teachers, students' ratings of course teachers, the impact of students on their own classroom listening, and the impact of mobile phones on their own classrooms; The evaluation indicators of students' classroom attitude include one or more of the following indicators: online classroom sign-in rate, course project participation and enthusiasm, and the behavior indicators also include online learning behavior indicators. The online learning behavior indicators include the following One or more of the metrics: video views, video watch duration, task point completion rate, total hits, chapter quiz completion rate, chapter quiz score, group score.
作为优选的技术方案，使用所述训练集对所述成绩预测模型进行训练具体为：As a preferred technical solution, using the training set to train the performance prediction model is specifically:
将训练样本输入所述成绩预测模型中，通过分类预测，获取各个元分类器输出的成绩等级概率数据，根据各个元分类器对应的成绩等级概率数据，获取预测等级，基于所述预测等级以及所述训练样本中的实际等级，完成对所述成绩预测模型的训练。Input the training samples into the performance prediction model, obtain the grade probability data output by each meta-classifier through classification prediction, obtain the prediction grade according to the grade probability data corresponding to each meta-classifier, and obtain the prediction grade based on the prediction grade and the obtained The actual grade in the training sample is used to complete the training of the performance prediction model.
作为优选的技术方案，根据各个元分类器对应的成绩等级概率数据，获取预测等级具体为：As a preferred technical solution, according to the grade probability data corresponding to each meta-classifier, the prediction grade is specifically obtained as follows:
将各个元分类器输出的概率数据进行加权平均，选取最高概率对应的等级作为所述预测等级。The probability data output by each meta-classifier is weighted and averaged, and the level corresponding to the highest probability is selected as the prediction level.
作为优选的技术方案，所述的成绩预测模型包括采用朴素贝叶斯算法、支持向量机以及C4.5决策树的元分类器。As a preferred technical solution, the grade prediction model includes a meta-classifier using a naive Bayesian algorithm, a support vector machine and a C4.5 decision tree.
本发明的另一个方面，提供了一种电子设备，包括：一个或多个处理器以及存储器，所述存储器内储存有一个或多个程序，所述一个或多个程序包括用于执行上述基于多路指标体系的预测成绩获取方法的指令。Another aspect of the present invention provides an electronic device, including: one or more processors and memory, one or more programs are stored in the memory, and the one or more programs are used to execute the above-mentioned Instructions on how to get the prediction score of the multi-way index system.
本发明的另一个方面，提供了一种计算机可读存储介质，包括供电子设备的一个或多个处理器执行的一个或多个程序，所述一个或多个程序包括用于执行上述基于多路指标体系的预测成绩获取方法的指令。Another aspect of the present invention provides a computer-readable storage medium, including one or more programs for execution by one or more processors of an electronic device, and the one or more programs include programs for executing the above multi-based Instructions on how to obtain the predicted performance of the road index system.
与现有技术相比，本发明具有以下优点：Compared with the prior art, the present invention has the following advantages:
(1)新背景下，通过基于包括课堂表现评价指标、学生课堂主观感受评价指标和学生课堂态度评价指标的行为指标构建具有多路指标体系的训练样本集，将学生在线学习行为和课堂学习行为整合为多路学生学习行为特征，完善了现背景下学生学习行为指标体系的不足，同时预测结果能够更全面地反应学生表现，通过训练融合多种成绩影响因素的成绩预测模型，有效提高了成绩预测准确性，从而解决或部分解决学生成绩影响因素变化导致学生成绩预测准确度较低的问题。(1) Under the new background, by constructing a training sample set with a multi-channel index system based on behavior indicators including classroom performance evaluation indicators, students’ classroom subjective feeling evaluation indicators and students’ classroom attitude evaluation indicators, students’ online learning behavior and classroom learning behavior Integrate into multi-channel student learning behavior characteristics, improve the deficiency of the student learning behavior index system in the current background, and predict the results to reflect the students' performance more comprehensively, and effectively improve the grades Prediction accuracy, so as to solve or partially solve the problem of low prediction accuracy of student performance caused by changes in factors affecting student performance.
(2)在训练过程中，使用了成熟的特征选择技术，通过主成分分析，得到了学生的多路特征之间的组合特征，有效去除了可能存在的冗余特征。(2) During the training process, the mature feature selection technology is used, and the combined features between the multi-channel features of the students are obtained through principal component analysis, which effectively removes possible redundant features.
(3)使用元分类器进行投票预测分类结果，解决或部分解决了由于不同分类器在不同课程数据集产生不同的预测结果，导致预测结果不准确的问题，互补了分类器之间优缺点，带来更准确的预测结果。(3) Use meta-classifiers to vote and predict classification results, which solves or partially solves the problem of inaccurate prediction results caused by different classifiers producing different prediction results in different course data sets, and complements the advantages and disadvantages of classifiers. lead to more accurate predictions.
附图说明Description of drawings
图1为实施例1中基于多路指标体系的预测成绩获取方法的流程图。FIG. 1 is a flow chart of the method for obtaining predicted grades based on the multi-way index system in Embodiment 1.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明的一部分实施例，而不是全部实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都应属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.
实施例1Example 1
如图1所述，本实施例针对翻转课堂的使用场景提供了一种基于多路指标体系的预测成绩获取方法。翻转课堂包括线上及线下两部分，本实施例的多路特征包括在线学习行为指标和线上学习行为指标，其中线上学习行为指标包括学生课堂表现、学生主观感受以及学生课堂态度。方法包括如下步骤：As shown in FIG. 1 , this embodiment provides a method for obtaining predicted grades based on a multi-way index system for the usage scenario of flipped classrooms. The flipped classroom includes two parts: online and offline. The multi-channel features of this embodiment include online learning behavior indicators and online learning behavior indicators, wherein the online learning behavior indicators include students' classroom performance, students' subjective feelings, and students' classroom attitudes. The method includes the following steps:
步骤S1，获取学习行为指标；Step S1, obtaining learning behavior indicators;
步骤S2，将学习行为指标输入预训练好的成绩预测模型中，所述的成绩预测模型包括采用朴素贝叶斯算法、支持向量机以及C4.5决策树的元分类器；Step S2, inputting the learning behavior indicators into the pre-trained performance prediction model, the performance prediction model includes a meta-classifier using Naive Bayesian algorithm, support vector machine and C4.5 decision tree;
步骤S3，获取成绩预测结果。Step S3, obtaining the result of the performance prediction.
其中，预训练好的成绩预测模型的获取步骤包括：Among them, the acquisition steps of the pre-trained grade prediction model include:
步骤S21，对线上直播课堂设计学生线上学习行为指标，用于每堂课后采集指标对应数据，其中，线上学习行为指标设计分为课堂表现记录、学生课堂主观感受和学生课堂态度，其中课堂表现记录包含：学生举手次数、学生回答次数、教师对学生回答的有效性判定；学生课堂主观感受包含：课堂内容的理解程度、教师所布置任务的难易程度评分、学生对该课程教师的评分、同学对自己的课堂听课影响、手机对自己的课堂影响；学生课堂态度包含：线上课堂签到率、课程项目参与度和积极度，设计在线学习行为指标，在线学习行为指标包括：视频观看量、视频观看时长、任务点完成率、总点击量、章节测验完成率、章节测验得分和小组评分。Step S21, design students' online learning behavior indicators for online live classes, and use them to collect data corresponding to the indicators after each class. Among them, the design of online learning behavior indicators is divided into classroom performance records, students' subjective classroom feelings, and students' classroom attitudes. Classroom performance records include: the number of times students raised their hands, the number of times students answered, and the teacher's judgment on the validity of students' answers; the subjective feelings of students in the classroom include: the degree of understanding of the classroom content, the difficulty rating of the tasks assigned by the teacher, and the students' evaluation of the course. Teachers' ratings, the influence of classmates on their classroom listening, and the impact of mobile phones on their own classrooms; students' classroom attitudes include: online classroom sign-in rate, course project participation and enthusiasm, and design online learning behavior indicators. Online learning behavior indicators include: Video Views, Video Watch Time, Mission Point Completion Rate, Total Clicks, Chapter Quiz Completion Rate, Chapter Quiz Score, and Group Rating.
步骤S22，整合所采集的线上直播课堂数据，得到学生线上学习行为数据，结合在线学习行为指标，得到多路特征，将该课程学生期末等级作为预测目标，对多路特征及目标特征进行预处理，再对多路特征通过主成分分析去除不必要的特征，得到处理后的学生数据集，其中，在线学习行为指标包含视频观看量、视频观看时长、任务点完成率、总点击量、章节测验完成率、章节测验得分、小组评分等，具体的，将学生线上学习行为数据及在线学习行为指标合并为多路特征，通过剔除或补充空值、异常值后，作归一化处理，然后由主成分分析得到互相组合的重要特征，得到处理后的学生多路特征数据集；Step S22, integrate the collected online live classroom data to obtain the online learning behavior data of students, combine the online learning behavior indicators to obtain multi-channel features, use the final grade of the students in the course as the prediction target, and perform multi-channel features and target features Preprocessing, and then performing principal component analysis on multi-channel features to remove unnecessary features, to obtain the processed student data set, in which the online learning behavior indicators include video viewing, video viewing duration, task point completion rate, total clicks, Chapter test completion rate, chapter test scores, group scores, etc. Specifically, the online learning behavior data of students and online learning behavior indicators are combined into multi-channel features, and normalized by removing or supplementing null values and outliers , and then the important features combined with each other are obtained by principal component analysis, and the processed student multi-channel feature data set is obtained;
步骤S23，将学生数据集根据7：3比例分层抽样划分为训练集和测试集，选取训练集放入设定好的成绩预测模型进行训练，将测试集放入训练完成的模型，损失函数值达到预设收敛条件后，得到预训练好的成绩预测模型，具体的，将划分出的训练集放入分类预测模型，每个元分类器各自(分批)训练各自的分类模型。将测试集放入训练好的分类模型，通过每个元分类器给出每个等级的概率进行加权平均，得到最终分类结果。Step S23, divide the student data set into a training set and a test set according to the 7:3 ratio of stratified sampling, select the training set and put it into the set grade prediction model for training, put the test set into the trained model, and use the loss function After the value reaches the preset convergence condition, a pre-trained performance prediction model is obtained. Specifically, the divided training set is put into the classification prediction model, and each meta-classifier trains its own classification model separately (in batches). The test set is put into the trained classification model, and the probability of each level given by each meta-classifier is weighted and averaged to obtain the final classification result.
其中，元分类器的定义为：在集成学习概念中，为了弥补单个分类器针对不同数据，预测结果可能不理想的情况，同时选取几个分类器一起预测，并对预测结果取平均或最大为最终结果，往往可以有效提升预测准确率。这几个分类器被称为元分类器。Among them, the definition of the meta-classifier is: in the concept of ensemble learning, in order to make up for the fact that a single classifier may not be ideal for different data, several classifiers are selected to predict together, and the average or maximum of the prediction results is The final result can often effectively improve the prediction accuracy. These several classifiers are called meta-classifiers.
与现有方法相比，提供一种在翻转课堂下基于多路指标体系的学生成绩预测方法，通过设计线上课堂学习行为指标，结合在线学习行为指标能够全面反映学生学习表现、评估学生成绩，本实施例具有以下有益效果：Compared with existing methods, this paper provides a student performance prediction method based on a multi-channel index system in a flipped classroom. By designing online classroom learning behavior indicators, combined with online learning behavior indicators, it can fully reflect student learning performance and evaluate student performance. This embodiment has the following beneficial effects:
一、本发明通过针对新背景下，将学生在线学习行为和课堂学习行为整合为多路学生学习行为特征，完善了现背景下学生学习行为指标体系的不足。然后通过模型预测，更全面地反应学生表现和学生成绩预测。1. According to the new background, the present invention integrates students' online learning behavior and classroom learning behavior into multiple student learning behavior characteristics, which improves the deficiency of the student learning behavior index system in the current background. Then through model prediction, it can more comprehensively reflect student performance and student achievement prediction.
二、本发明在数据处理后，使用了成熟的特征选择技术。通过主成分分析，得到了学生学习行为多路特征之间的组合特征，有效去除了可能存在的冗余特征。Two, the present invention uses mature feature selection technology after data processing. Through principal component analysis, the combined features of the multi-channel features of students' learning behavior are obtained, and the possible redundant features are effectively removed.
三、使用元分类器进行投票预测分类结果，解决了不同分类器在不同课程数据集产生不同的预测结果，互补了分类器之间优缺点，带来更准确的预测结果。3. Use meta-classifiers to vote and predict classification results, which solves the problem that different classifiers produce different prediction results in different course data sets, complements the advantages and disadvantages of classifiers, and brings more accurate prediction results.
实施例2Example 2
本实施例提供了一种电子设备，包括：一个或多个处理器以及存储器，所述存储器内储存有一个或多个程序，所述一个或多个程序包括用于执行如实施例1所述基于多路指标体系的预测成绩获取方法的指令。This embodiment provides an electronic device, including: one or more processors and a memory, one or more programs are stored in the memory, and the one or more programs are used to execute the Instructions for how to obtain prediction scores based on the multi-way index system.
实施例3Example 3
本实施例提供了一种计算机可读存储介质，包括供电子设备的一个或多个处理器执行的一个或多个程序，所述一个或多个程序包括用于执行如实施例1所述基于多路指标体系的预测成绩获取方法的指令。This embodiment provides a computer-readable storage medium, including one or more programs for execution by one or more processors of an electronic device, and the one or more programs include a Instructions on how to get the prediction score of the multi-way index system.
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily think of various equivalents within the technical scope disclosed in the present invention. Modifications or replacements shall all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211690722.5ACN116167499A (en) | 2022-12-27 | 2022-12-27 | Prediction result acquisition method, equipment and medium based on multi-path index system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211690722.5ACN116167499A (en) | 2022-12-27 | 2022-12-27 | Prediction result acquisition method, equipment and medium based on multi-path index system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116167499Atrue CN116167499A (en) | 2023-05-26 |
Family
ID=86417448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211690722.5APendingCN116167499A (en) | 2022-12-27 | 2022-12-27 | Prediction result acquisition method, equipment and medium based on multi-path index system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167499A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118378753A (en)* | 2024-05-28 | 2024-07-23 | 江苏师范大学 | Dual-hybrid teaching learning effect prediction and promotion method |
- 2022
- 2022-12-27CNCN202211690722.5Apatent/CN116167499A/enactivePending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118378753A (en)* | 2024-05-28 | 2024-07-23 | 江苏师范大学 | Dual-hybrid teaching learning effect prediction and promotion method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ashenafi et al. | Predicting students' final exam scores from their course activities | |
| CN111062842A (en) | Method and device for dynamically generating personalized questions | |
| CN109636690B (en) | Learning effectiveness comprehensive scoring method based on online learning behavior data of learner | |
| Kai et al. | Predicting Student Retention from Behavior in an Online Orientation Course. | |
| CN103577507A (en) | Intelligent question bank system with real-time detection and self-adaptive evolution mechanism and method | |
| CN113535982A (en) | A teaching system based on big data | |
| CN111639860A (en) | Online education system based on mathematical model and shift distributing method thereof | |
| Giancola et al. | Chain effects in diachronic perspective. Social inequalities and school-tracks-choices affecting educational outcomes in Italy | |
| Cui et al. | College Mathematics Teaching Method Based on Big Data. | |
| Paris et al. | The Impact of Optional: Investigating the Effects of Test-Optional Admissions Policies. | |
| CN116167499A (en) | Prediction result acquisition method, equipment and medium based on multi-path index system | |
| Holtmann et al. | The double-edged sword of de-tracking reforms in Germany: Using a Difference-in-Differences approach to estimate effects on students' educational aspirations and their association with students' socioeconomic backgrounds | |
| Saleh et al. | Predicting student performance using data mining and learning analysis technique in Libyan Higher Education | |
| Marion et al. | Considerations for Analyzing Educators’ Contributions to Student Learning in Non-tested | |
| CN113409635A (en) | Interactive teaching method and system based on virtual reality scene | |
| May et al. | A longitudinal study of the impact of America's Choice on student performance in Rochester, New York, 1998-2003 | |
| CN117556381A (en) | A deep knowledge mining method and system for interdisciplinary subjective test questions | |
| CN116228044A (en) | Mathematics core literacy assessment method and system based on neural network and random forest | |
| Shi et al. | Stay or leave? Exploring student factors associated with dropout patterns in massive open online courses | |
| CN116993004A (en) | Teaching evaluation method and device based on double-layer index system | |
| Shoukat et al. | Investigating the Impact of Inclusive Education Policies on the Academic Performance of Students with Diverse Abilities | |
| Yeung et al. | Evaluating the effectiveness of ai-based essay grading tools in the summative assessment of higher education | |
| CN116109456A (en) | A comprehensive evaluation method, system, electronic equipment and storage medium for smart education | |
| Zhang et al. | English Distance teaching based on SPOC classroom and online mixed teaching mode | |
| CN114582182A (en) | Accurate teaching and learning system for large data of quasi-teaching wisdom |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |