Autonomous learning concentration degree real-time generating method based on online learning behavior

Abstract

The invention discloses an autonomous learning concentration degree real-time generating method based on an online learning behavior. The method comprises the following steps of S1, forming an autonomous learning concentration degree displaying parameter Es by a video playing parameter, a viewing time length parameter and a concurrent behavior parameter, and forming a learning concentration degreeexpression formula; S2, respectively constructing a data two-dimensional matrix; and S3, through a concentration degree total parameter Es which is composed of three parameters of P1, Rt and Pa, comprehensively reflecting a learning concentration condition which is reflected in each behavior in the online learning process. The method suggests generation of the concentration degree parameter Es according to a teaching video playing behavior, a video viewing time length and concurrent learning behavior data, and acquisition of online learning concentration degree data is automated and simplified, and real-time concentration degree data acquisition and process analysis become possible, thereby totally changing a current analysis thought and method for the online learning concentration degree, so that online learning process guidance and analysis based on data supporting become possible.

Description

technical field [0001] The present invention relates to the technical field of online autonomous learning, and more specifically, relates to a real-time generation method of autonomous learning input based on online learning behavior. Background technique [0002] Since 2012, with the vigorous construction and wide application of MOOC, open video courses, and various open online courses, people have gradually shifted their focus from the construction of online learning resources (OER) and online courses (OC) to the learning quality of online courses. and effects. For this reason, the industry tries to analyze the quality and effect of learners in terms of academic performance, engagement, satisfaction, and participation, among which online learning engagement has become one of the important indicators. Online learning includes independent learning and collaborative learning. The learning input is constantly changing with the development of the two learning methods. As long ...

AI Technical Summary

Problems solved by technology

The implementation of these methods is time-consuming and difficult to carry out dynamically. The results are highly subjective, and the succession and comparability of different standards are weak. Therefore, it is difficult to generate quantitative indicators of engagement in real time, and cannot reflect students' online learning in real time and intuitively. The investment performance and development of independent learning, and the evaluation results are also difficult to use for vertical and horizontal comparisons. The main reasons for these problems are as follows:

[0007] 1. Constrained by traditional engagement analysis methods, they did not recognize the role of data in online learning platforms, and did not make full use of the rich data such as behavioral data, interaction data, and evaluation data generated during the online learning process to conduct engagement analysis

[0008] 2. Using scales and surveys to analyze the learning engagement in the whole process of online learning. There are too many focus points and the types of online learning activities involved are complicated. Therefore, the scales formed have many items and complicated questions, which are difficult to carry out at any time, and difficult to understand. Use consistent input parameters to express the results and make comparisons and judgments, requiring human intervention for analysis and interpretation

[0009] 3. The survey of the scale needs to mobilize the cooperation of students, and it cannot be automatically generated during the learning process, so it is difficult to follow the online learning process to analyze the engagement degree at any time

[0010] Although the establishment of gauges is based on certain theories, the process of scale establishment and data analysis is highly subjective, and the process of evaluation materials and data collection and analysis consumes a lot of manpower, material and financial resources, and the subjectivity of the problems occupies a certain amount. Ratio, which will affect the objectivity of input level analysis

Analysis results are usually expressed in the form of scores or ratings, which require further interpretation based on professional knowledge to truly clarify the meaning of the scores or grades. No online learning platform has adopted this method for real-time analysis of normalized engagement

Images