阅读说明：本技术 一种在线教育平台 (Online education platform ) 是由 纪国庆 于 2020-04-23 设计创作，主要内容包括：本发明提供一种在线教育平台,涉及在线教育领域,包括反作弊检测系统和个性化学习推荐系统；反作弊检测系统包括考试数据获取模块和反作弊检测模块；考试数据获取模块使用ELK分析工具实时获取学生考试的日志文件,提取学生考试行为数据；反作弊检测模块将学生考试行为数据输入反作弊机器模型进行识别,检测是否存在作弊行为；个性化学习推荐系统包括学习数据获取模块和学习推荐模块；学习数据获取模块使用ELK分析工具实时获取学生学习的日志文件,提取学生学习数据；学习推荐模块对学生学习数据和候选推荐习题进行多维特征计算,获取个性化学习推荐。本发明解决了现有技术中在线教育平台相对僵化,功能单一,不能满足在线教育需求的问题。(The invention provides an online education platform, which relates to the field of online education and comprises an anti-cheating detection system and an individualized learning recommendation system; the anti-cheating detection system comprises an examination data acquisition module and an anti-cheating detection module; the examination data acquisition module acquires a log file of the student examination in real time by using an ELK analysis tool and extracts examination behavior data of the student; the anti-cheating detection module inputs the examination behavior data of the students into an anti-cheating machine model for recognition and detects whether cheating behaviors exist or not; the personalized learning recommendation system comprises a learning data acquisition module and a learning recommendation module; the learning data acquisition module acquires a student learning log file in real time by using an ELK analysis tool and extracts student learning data; and the learning recommendation module performs multidimensional characteristic calculation on the student learning data and the candidate recommendation exercises to obtain personalized learning recommendation. The invention solves the problems that the online education platform in the prior art is relatively rigid, has single function and can not meet the online education requirement.)

1. An online education platform, characterized in that: the online education platform comprises an anti-cheating detection system and an individualized learning recommendation system;

the anti-cheating detection system comprises an examination data acquisition module and an anti-cheating detection module;

the examination data acquisition module acquires a log file of the student examination in real time by using an ELK analysis tool and extracts examination behavior data of the student;

the anti-cheating detection module inputs the examination behavior data of the students into an anti-cheating machine model for identification and detects whether cheating behaviors exist or not;

the personalized learning recommendation system comprises a learning data acquisition module and a learning recommendation module;

the learning data acquisition module acquires a student learning log file in real time by using an ELK analysis tool and extracts student learning data;

the learning recommendation module performs multidimensional feature calculation on the learning data of the students to obtain personalized learning recommendation.

2. An online education platform according to claim 1, wherein: the anti-cheating machine model needs to be trained before being identified, and the anti-cheating machine model training process is as follows:

s1.1: acquiring historical examination data of students, and performing characteristic processing on the historical examination data to obtain abnormal behavior data in the historical data;

s1.2: establishing a knowledge base according to the historical data of the feature processing, and establishing a machine learning model;

s1.3: and inputting the abnormal behavior data and the abnormal labels in the knowledge base into a machine learning module for model training, calculating the quantity of the abnormal behavior data, and outputting an abnormal cheating early warning signal if the quantity of the abnormal behavior data exceeds a preset threshold value.

3. The online education platform of claim 1, wherein the learning recommendation module has a workflow of:

s2.1: acquiring historical learning data of students, and performing feature processing on the historical learning data to obtain historical learning features;

s2.2: constructing a problem correlation network according to the knowledge correlation degree between the problems;

in the problem correlation network, one node represents one problem, connecting lines among the nodes represent the correlation between the problems, the weight of the connecting lines represents the knowledge correlation between the problems, and the cosine similarity algorithm is used for calculating the knowledge correlation;

s2.3: and linearly integrating the factors of the three dimensions through a multi-dimensional characteristic algorithm to obtain the overall correlation degree between the students and the candidate recommendation exercises, ranking the overall correlation degree of all the candidate recommendation exercises, and outputting personalized learning recommendation.

4. An online education platform according to claim 1, wherein: the online education platform also comprises a teacher management system; the teacher management system comprises a teacher management module, a teaching management module and a problem management module;

the teacher management module is used for teacher account information management, account password information management and account login information management;

the teaching management module is used for uploading a course content list, playing an online video, generating a video watching report and managing course chapter evaluation;

the exercise management module is used for uploading the after-class exercise content list and the after-class exercise.

5. An online education platform according to claim 4, wherein: the teaching management module comprises a course content list, an online video player, a video watching report unit, a chapter evaluation unit and a chapter evaluation report unit;

the course content list provides course titles, chapters and section names, and provides playing links from each chapter and section name to corresponding course live broadcast video files and recorded video files;

the online video player plays corresponding chapters, lesson programs live video files and recorded video files according to the playing request of the student;

the video watching report unit monitors the playing time of each chapter, program live video file and recorded video file played by students, and generates a visual report by statistics;

the chapter evaluation unit monitors the playing conditions of each chapter, lesson program live video file and recorded video file played by students, and after each chapter, lesson program live video file and recorded video file are played, an evaluation test question corresponding to the lesson program is popped up in a dialog box mode for the students to input answers;

and the chapter evaluation report unit counts the correct rate of the answers according to the answers input by the students and generates a visual report.

6. An online education platform according to claim 1, wherein: the online education platform also comprises a student management system, wherein the student management system comprises a student management module, a course management module and a problem module;

the student management module is used for student account information management, account password information management and account login information management;

the course management module is used for reminding course time, storing course chapter notes and storing course chapter evaluation results;

the exercise module is used for obtaining the after-class exercise content list and the after-class exercise.

Technical Field

The invention relates to the field of online education, in particular to an online education platform.

Background

The online education platform, namely the online training system is tool software for implementing online training and online education, and is a remote online education college which can be customized and expanded by using a network technology and a software technology. The system helps the industry or enterprises to quickly build a self-proprietary knowledge base system through simple and easy-to-use courseware and test question importing and manufacturing functions, and provides functions of training requirement investigation, training target setting, course system design, training plan management, training process monitoring, examination evaluation and the like to help clients to efficiently implement staff training and examination tasks.

The traditional online education platform has the traditional functions of account management, live video, video playback, courseware uploading, test question importing, online examination and the like. However, the traditional online education system is relatively rigid, has incomplete functions and cannot meet the online education requirements. For example, when an online examination is performed, anti-cheating detection and early warning cannot be performed, and a personalized learning scheme, post-session exercise, and the like cannot be recommended for the comprehensive ability of students.

Disclosure of Invention

In view of the above disadvantages of the prior art, an object of the present invention is to provide an online education platform, which is used to solve the problems that the online education platform in the prior art is relatively rigid, has a single function, and cannot meet the requirements of online education.

The invention provides an online education platform, which comprises an anti-cheating detection system and an individualized learning recommendation system;

the anti-cheating detection system comprises an examination data acquisition module and an anti-cheating detection module;

the examination data acquisition module acquires a log file of the student examination in real time by using an ELK analysis tool and extracts examination behavior data of the student;

the anti-cheating detection module inputs the examination behavior data of the students into an anti-cheating machine model for identification and detects whether cheating behaviors exist or not;

the personalized learning recommendation system comprises a learning data acquisition module and a learning recommendation module;

the learning data acquisition module acquires a student learning log file in real time by using an ELK analysis tool and extracts student learning data;

the learning recommendation module performs multidimensional feature calculation on the learning data of the students to obtain personalized learning recommendation.

According to the invention, examination behavior data of online learning of students are collected, and the behavior data is input into a pre-trained anti-cheating machine model for identification, so that whether cheating behaviors exist can be detected through the anti-cheating machine model; meanwhile, the learning data of the students are obtained, multi-dimensional feature calculation is carried out on the basis of the learning features, the overall correlation between the students and the candidate recommendation exercises is obtained, the overall correlation of all the candidate recommendation exercises is ranked, and personalized learning recommendation is output; the anti-cheating detection and early warning can be realized, meanwhile, an individualized learning scheme can be recommended according to the comprehensive ability of students, and the online education requirement can be met.

In an embodiment of the present invention, before the anti-cheating machine model is identified, anti-cheating machine model training needs to be performed, where the anti-cheating machine model training process includes:

s1.1: acquiring historical examination data of students, and performing characteristic processing on the historical examination data to obtain abnormal behavior data in the historical data;

s1.2: establishing a knowledge base according to the historical data of the feature processing, and establishing a machine learning model;

s1.3: and inputting the abnormal behavior data and the abnormal labels in the knowledge base into a machine learning module for model training, calculating the quantity of the abnormal behavior data, and outputting an abnormal cheating early warning signal if the quantity of the abnormal behavior data exceeds a preset threshold value.

In an embodiment of the present invention, the work flow of the learning recommendation module is:

s2.1: acquiring historical learning data of students, and performing feature processing on the historical learning data to obtain historical learning features;

s2.2: constructing a problem correlation network according to the knowledge correlation degree between the problems;

in the problem correlation network, one node represents one problem, connecting lines among the nodes represent the correlation between the problems, the weight of the connecting lines represents the knowledge correlation between the problems, and the cosine similarity algorithm is used for calculating the knowledge correlation;

s2.3: and linearly integrating the factors of the three dimensions through a multi-dimensional characteristic algorithm to obtain the overall correlation degree between the students and the candidate recommendation exercises, ranking the overall correlation degree of all the candidate recommendation exercises, and outputting personalized learning recommendation.

In an embodiment of the invention, the online education platform further comprises a teacher management system; the teacher management system comprises a teacher management module, a teaching management module and a problem management module;

the teacher management module is used for teacher account information management, account password information management and account login information management;

the teaching management module is used for uploading a course content list, playing an online video, generating a video watching report and managing course chapter evaluation;

the exercise management module is used for uploading the after-class exercise content list and the after-class exercise.

In one embodiment of the invention, the teaching management module comprises a course content list, an online video player, a video watching report unit, a chapter evaluation unit and a chapter evaluation report unit;

the course content list provides course titles, chapters and section names, and provides playing links from each chapter and section name to corresponding course live broadcast video files and recorded video files;

the online video player plays corresponding chapters, lesson programs live video files and recorded video files according to the playing request of the student;

the video watching report unit monitors the playing time of each chapter, program live video file and recorded video file played by students, and generates a visual report by statistics;

the chapter evaluation unit monitors the playing conditions of each chapter, lesson program live video file and recorded video file played by students, and after each chapter, lesson program live video file and recorded video file are played, an evaluation test question corresponding to the lesson program is popped up in a dialog box mode for the students to input answers;

and the chapter evaluation report unit counts the correct rate of the answers according to the answers input by the students and generates a visual report.

In an embodiment of the invention, the online education platform further comprises a student management system, wherein the student management system comprises a student management module, a course management module and a problem learning module;

the student management module is used for student account information management, account password information management and account login information management;

the course management module is used for reminding course time, storing course chapter notes and storing course chapter evaluation results;

the exercise module is used for obtaining the after-class exercise content list and the after-class exercise.

As described above, the online education platform of the present invention has the following advantages: according to the invention, examination behavior data of online learning of students are collected, and the behavior data is input into a pre-trained anti-cheating machine model for identification, so that whether cheating behaviors exist can be detected through the anti-cheating machine model; meanwhile, learning data of students are obtained, multidimensional feature calculation is carried out on the basis of learning features, overall correlation between the students and the candidate recommendation exercises is obtained, the overall correlation of all the candidate recommendation exercises is ranked, and personalized learning recommendation is output; the anti-cheating detection and early warning can be realized, meanwhile, an individualized learning scheme can be recommended according to the comprehensive ability of students, and the online education requirement can be met.

Drawings

Fig. 1 is a block diagram showing the structure of an online education platform disclosed in the embodiment of the present invention.

Fig. 2 is a block diagram showing a configuration of the teacher management system disclosed in the embodiment of the present invention.

Fig. 3 is a block diagram showing the structure of the student management system disclosed in the embodiment of the present invention.

Fig. 4 is a block diagram illustrating the structure of the anti-cheating detection system disclosed in the embodiment of the present invention.

FIG. 5 is a flowchart illustrating the training process of the anti-cheating machine model disclosed in the embodiment of the present invention.

Fig. 6 is a block diagram illustrating a structure of the personalized learning recommendation system disclosed in the embodiment of the present invention.

Fig. 7 is a flowchart illustrating the operation of the learning recommendation module disclosed in the embodiment of the present invention.

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

Referring to fig. 1, the present invention provides an online education platform including a teacher management system, a student management system, an anti-cheating detection system, and a personalized learning recommendation system.

Referring to fig. 2, the teacher management system includes a teacher management module, a teaching management module, and a problem management module;

the teacher management module is used for teacher account information management, account password information management and account login information management;

the teaching management module is used for uploading a course content list, playing an online video, generating a video watching report and managing course chapter evaluation;

the teaching management module comprises a course content list, an online video player, a video watching report unit, a chapter evaluation unit and a chapter evaluation report unit;

the course content list provides course titles, chapters and section names, and provides playing links from each chapter and section name to corresponding course live broadcast video files and recorded video files;

the online video player plays corresponding chapters, lesson programs live video files and recorded video files according to the playing request of the student;

the video watching report unit monitors the playing time of each chapter, program live video file and recorded video file played by students, and generates a visual report by statistics;

the chapter evaluation unit monitors the playing conditions of each chapter, lesson program live video file and recorded video file played by students, and after each chapter, lesson program live video file and recorded video file are played, an evaluation test question corresponding to the lesson program is popped up in a dialog box mode for the students to input answers;

and the chapter evaluation report unit counts the correct rate of the answers according to the answers input by the students and generates a visual report.

The exercise management module is used for uploading the after-class exercise content list and the after-class exercise.

Referring to fig. 3, the student management system includes a student management module, a course management module, and a problem module;

the student management module is used for student account information management, account password information management and account login information management;

the course management module is used for reminding course time, storing course chapter notes and storing course chapter evaluation results;

the exercise module is used for obtaining the after-class exercise content list and the after-class exercise.

Referring to fig. 4, the anti-cheating detection system includes an examination data acquisition module and an anti-cheating detection module;

the examination data acquisition module acquires a log file of the student examination in real time by using an ELK analysis tool and extracts examination behavior data of the student;

the log file is used for storing examination video images, chapter tests and examination operations of students and generating continuously updated data; historical learning behavior data and current real-time online behavior data of the examinee can be clearly and accurately extracted from the log file, so that comprehensive estimation and anomaly detection can be conveniently carried out on examination behaviors of the examinee in the follow-up process, and the accuracy and timeliness of anti-cheating detection are improved.

The anti-cheating detection module inputs the examination behavior data of the students into an anti-cheating machine model for identification and detects whether cheating behaviors exist or not;

referring to fig. 5, before the anti-cheating machine model is identified, anti-cheating machine model training needs to be performed, where the anti-cheating machine model training process includes:

s1.1: acquiring historical examination data of students, and performing characteristic processing on the historical examination data to obtain abnormal behavior data in the historical data;

s1.2: establishing a knowledge base according to the historical data of the feature processing, and establishing a machine learning model;

s1.3: and inputting the abnormal behavior data and the abnormal labels in the knowledge base into a machine learning module for model training, calculating the quantity of the abnormal behavior data, and outputting an abnormal cheating early warning signal if the quantity of the abnormal behavior data exceeds a preset threshold value.

Referring to fig. 6, the personalized learning recommendation system includes a learning data acquisition module and a learning recommendation module;

the learning data acquisition module acquires a student learning log file in real time by using an ELK analysis tool and extracts student learning data;

and the learning recommendation module performs multidimensional characteristic calculation on the student learning data and the candidate recommendation exercises to obtain personalized learning recommendation.

Referring to fig. 7, the work flow of the learning recommendation module is as follows:

s2.1: acquiring historical learning data of students, and performing feature processing on the historical learning data to obtain historical learning features;

s2.2: constructing a problem correlation network according to the knowledge correlation degree between the problems;

in the problem correlation network, one node represents one problem, connecting lines among the nodes represent the correlation between the problems, the weight of the connecting lines represents the knowledge correlation between the problems, and the cosine similarity algorithm is used for calculating the knowledge correlation;

s2.3: and linearly integrating the factors of the three dimensions through a multi-dimensional characteristic algorithm to obtain the overall correlation degree between the students and the candidate recommendation exercises, ranking the overall correlation degree of all the candidate recommendation exercises, and outputting the sexual learning recommendation.

The overall correlation Cor (L, S) between student L and candidate recommendation problem S is formulated as follows: cor (L, S) ═ a × nor (pop (S)) + b × nor (ls (S)) + c × nor (Kr (L, S)), where nor (x) ═ x/max (x) indicates the normalization of a certain dimension; normalizing the values of the three dimensions, weighting and summing, and adjusting parameters through feedback results to optimize the parameters; and finally, ranking all the candidate recommended exercises, and recommending the optimal candidate exercises to students.

In conclusion, the invention can detect whether cheating behaviors exist or not by collecting examination behavior data of online learning of students and inputting the behavior data into the pre-trained anti-cheating machine model for identification; meanwhile, the learning data of the students are obtained, multi-dimensional feature calculation is carried out on the basis of the learning features, the overall correlation between the students and the candidate recommendation exercises is obtained, the overall correlation of all the candidate recommendation exercises is ranked, and personalized learning recommendation is output; the anti-cheating detection and early warning can be realized, meanwhile, an individualized learning scheme can be recommended according to the comprehensive ability of students, and the online education requirement can be met. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.