阅读说明：本技术 基于大数据平台的个性化学习方法及系统 (Individual learning method and system based on big data platform ) 是由 王磊 牛林 李宏博 张振海 马志广 司泰龙 商玲玲 郭丽娟 陈丽娜 于 2021-07-19 设计创作，主要内容包括：本公开公开了一种基于大数据平台的个性化学习方法,包括：建立包含学生信息库、反馈数据库、培训知识库和兴趣知识资源库的大数据平台,并实时更新大数据平台内的数据；向培训知识库录入培养知识,向学生信息库录入学生信息、学生的测评成绩和教学目标；向大数据平台提出服务请求；根据服务请求,结合测评成绩和教学目标,将培训知识库和兴趣知识资源库内的相关信息进行反馈；本公开将大数据分析与个性化定制学习相结合,利用大数据管理各种知识资源,并分析学生自主学习行为以及考核评价指标,将分析结果转化为学习内容推送机制,有助于解决目前个性化学习方法不足的问题。(The disclosure discloses a personalized learning method based on a big data platform, which comprises the following steps: establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time; inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base; a service request is made to a big data platform; according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target; the method combines big data analysis and personalized customization learning, manages various knowledge resources by using big data, analyzes autonomous learning behaviors and evaluation indexes of students, converts analysis results into a learning content pushing mechanism, and is beneficial to solving the problem of insufficient current personalized learning methods.)

1. The personalized learning method based on the big data platform is characterized by comprising the following steps:

establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base;

a service request is made to a big data platform;

and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

2. The big-data-platform-based personality learning method of claim 1, wherein the big data platform comprises a ZooKeeper layer, a Hadoop layer, and an Apache Spark layer;

the ZooKeeper layer comprises a plurality of data storage devices packaged into a cluster form; the ZooKeeper provides the calculation and storage functions which can be provided by the data storage equipment managed in the cluster to the Hadoop in the form of an interface;

the Hadoop is used for managing personalized customization data in the big data platform;

apache Spark is used for the computation and analysis of data sets within the data platform.

3. The big data platform-based personalized learning method of claim 2, wherein the data storage devices comprise at least a network university server, a student information server, a digital library and an examination system;

the big data platform fuses video resources on a network university server, electronic books in a digital library, student feedback information in a student information server and test scores in an examination system, and forms a virtual resource domain by means of the personalized customization module.

4. The big data platform-based personalized learning method of claim 2, wherein the personalized customization data comprises at least electronic books, video courseware, student access records, examination achievement analysis and student feedback records.

5. The big data platform based personalized learning method of claim 1, wherein the big data platform obtains knowledge resources that are of interest to students according to ID numbers accessed by the students, and pushes related category learning resources to the students for extended learning.

6. Individualized learning system based on big data platform, its characterized in that includes: the system comprises a database establishing module, an information interaction module and an information feedback module;

the data establishment module configured to: establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

the information interaction module is configured to: inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base; a service request is made to a big data platform;

the information feedback module configured to: and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

7. The big data platform based personalized learning system of claim 6, wherein the big data platform comprises a ZooKeeper layer, a Hadoop layer, and an Apache Spark layer;

the ZooKeeper layer comprises a plurality of data storage devices packaged into a cluster form; the ZooKeeper provides the calculation and storage functions which can be provided by the data storage equipment managed in the cluster to the Hadoop in the form of an interface;

the Hadoop is used for managing personalized customization data in the big data platform;

apache Spark is used for the computation and analysis of data sets within the data platform.

8. The big data platform-based personalized learning system of claim 7, wherein the data storage devices comprise at least a network university server, a student information server, a digital library and an examination system;

the big data platform fuses video resources on a network university server, electronic books in a digital library, student feedback information in a student information server and test scores in an examination system, and forms a virtual resource domain by means of the personalized customization module.

9. The big data platform based personalized learning system of claim 7, wherein the personalized customization data comprises at least electronic books, video courseware, student access records, examination achievement analysis and student feedback records.

10. The big data platform based personalized learning system of claim 6, wherein the big data platform obtains knowledge resources that are of interest to students according to ID numbers accessed by the students, and pushes related category learning resources to the students for extended learning.

Technical Field

The disclosure belongs to the technical field of personalized learning, and particularly relates to a personalized learning method and system based on a big data platform.

Background

The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.

From the application of the current big data in professional education, the application of the big data in the concept of macroscopic management of the professional education, including the application in the aspects of data center construction, data management and learning environment construction, has certain effect; however, there are two key issues, firstly, the application of big data in student learning ability assessment is not sufficient, and secondly, the technology and tools based on big data are relatively few in practical application.

The inventor finds that in the field of professional education, a lot of research has been carried out by applying big data, particularly in the aspects of macroscopic management, resource bank construction, modern apprentice system and talent culture; but many researches have the defects of insufficient systematization, insufficient comprehension and lack of empirical foundation; personalized learning is also gradually started in the field of professional education, but is not popularized and applied.

The problems generally exist in the current vocational colleges, the learning efficiency of students is seriously restricted, and the improvement of the learning efficiency is not facilitated.

Disclosure of Invention

In order to solve the above problems, the present disclosure provides a method and a system for personalized learning based on a big data platform; the method combines big data analysis and personalized customization learning, manages various knowledge resources by using big data, analyzes autonomous learning behaviors and evaluation indexes of students, converts analysis results into a learning content pushing mechanism, and is beneficial to solving the problem of insufficient current personalized learning methods.

In order to achieve the above object, in a first aspect, the present disclosure provides a method for personalized learning based on a big data platform, which adopts the following technical scheme:

the personalized learning method based on the big data platform comprises the following steps:

establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base;

a service request is made to a big data platform;

and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

Further, the big data platform comprises a ZooKeeper layer, a Hadoop layer and an Apache Spark layer;

the ZooKeeper layer comprises a plurality of data storage devices packaged into a cluster form; the ZooKeeper provides the calculation and storage functions which can be provided by the data storage equipment managed in the cluster to the Hadoop in the form of an interface;

the Hadoop is used for managing personalized customization data in the big data platform;

apache Spark is used for the computation and analysis of data sets within the data platform.

Further, the data storage device at least comprises a network university server, a student information server, a digital library and an examination system;

the big data platform fuses video resources on a network university server, electronic books in a digital library, student feedback information in a student information server and test scores in an examination system, and forms a virtual resource domain by means of the personalized customization module.

Further, the personalized customization data at least comprises electronic books, video courseware, student access records, examination score analysis and student feedback records.

Furthermore, the big data platform acquires knowledge resources interested by the students according to ID numbers accessed by the students and pushes the learning resources of related categories to the students for extended learning.

In order to achieve the above object, in a second aspect, the present disclosure further provides a personalized learning system based on a big data platform, which adopts the following technical scheme:

personalized learning system based on big data platform, including: the system comprises a database establishing module, an information interaction module and an information feedback module;

the data establishment module configured to: establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

the information interaction module is configured to: inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base; a service request is made to a big data platform;

the information feedback module configured to: and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

Further, the big data platform comprises a ZooKeeper layer, a Hadoop layer and an Apache Spark layer;

the ZooKeeper layer comprises a plurality of data storage devices packaged into a cluster form; the ZooKeeper provides the calculation and storage functions which can be provided by the data storage equipment managed in the cluster to the Hadoop in the form of an interface;

the Hadoop is used for managing personalized customization data in the big data platform;

apache Spark is used for the computation and analysis of data sets within the data platform.

Further, the data storage device at least comprises a network university server, a student information server, a digital library and an examination system;

the big data platform fuses video resources on a network university server, electronic books in a digital library, student feedback information in a student information server and test scores in an examination system, and forms a virtual resource domain by means of the personalized customization module.

Further, the personalized customization data at least comprises electronic books, video courseware, student access records, examination score analysis and student feedback records.

Furthermore, the big data platform acquires knowledge resources interested by the students according to ID numbers accessed by the students and pushes the learning resources of related categories to the students for extended learning.

Compared with the prior art, the beneficial effect of this disclosure is:

1. the teaching resources are integrated through big data, a knowledge representation method, field attributes and a knowledge storage mode of a student training knowledge base are researched, and an association method of individual learning and the knowledge base of a student is designed based on a big data platform, so that the training knowledge base is seamlessly connected with the individual learning of the student;

2. according to the method, requirements and short boards of the culture feedback and the network evaluation results of students are integrated into actual culture according to the definition of individual customization, the culture quality is improved in an individual customization mode, and the precedent of individual customization is developed for professional education;

3. according to the method, the student is cultured by utilizing the personalized customization method, and the culture quality is improved.

Drawings

The accompanying drawings, which form a part hereof, are included to provide a further understanding of the present embodiments, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the present embodiments and together with the description serve to explain the present embodiments without unduly limiting the present embodiments.

FIG. 1 is a three-level design of the system of the present disclosure and its associations;

FIG. 2 is a block diagram of a big data platform of the present disclosure.

The specific implementation mode is as follows:

the present disclosure is further described with reference to the following drawings and examples.

It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

Example 1:

the disclosure provides a personalized learning method based on a big data platform, which comprises the following steps:

establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base;

a service request is made to a big data platform;

and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

Through this embodiment, can combine the teaching target according to respective cultivation expectation, evaluation score and the Web knowledge point access record of student, the automatic analysis goes out student's interest point and not enough point, and then provides the electronization tutor after class to promote the cultivation effect, improve and cultivate the quality.

In this embodiment, the design scheme of the big data platform is as follows:

the big data platform provides basic data and real-time data, wherein the student information database comprises data such as student numbers, student names, classes, culture delivery units and the like, and is convenient for students to safely log in at any time to check arrangement conditions needing training. The big data platform establishes a database and an application system thereof under a specific application environment, so that the database and the application system can effectively store data, provide mapping processing of a data table in a local knowledge base and a business object, comprise various data processing components or services, are called by a business logic layer, shield the difference of specific database access realization technology, and realize the access to a bottom system database; the application requirements of various students including feedback requirements and learning requirements are met; the design of a good data platform can not only improve the overall performance of the system, but also improve the development quality and the development efficiency.

In this embodiment, the big data is mainly collected from 4 sources according to the classification of the application system for generating data by MapReduce: a network university data set, a digital library data set, a web site data set and a culture course related data set; for different data sets, different structures and modes may exist, such as files, XML trees, relational tables, and the like, which are expressed as data heterogeneity; performing further integrated processing or integration processing on a plurality of heterogeneous data sets, collecting, sorting, cleaning and converting data from different data sets to generate a new data set, and providing a uniform data view for subsequent query and analysis processing; in addition, in the embodiment, the database and the knowledge base are optimized, so that the database can more accurately represent business data, the database is easy to use and maintain and can quickly respond to users, data modification and data retrieval are facilitated, an effective safety mechanism is provided to ensure the safety of data, and redundant data are reduced.

Specifically, as shown in fig. 2, in the big data platform, preferably, the bottom layer is a distributed collaboration service cluster built by ZooKeeper; the ZooKeeper is a reliable coordination system for providing consistency service for distributed application, and can provide functions of configuration maintenance, domain name service, distributed synchronization and the like for a server cluster; the ZooKeeper packages data storage devices such as a network university server, a student information server, a digital library, an examination system and the like into a cluster form, so that storage nodes in the data storage devices are backups for each other, and when a certain server goes down, the extraction of fault data is not influenced or the computing capacity of the cluster is not reduced.

The ZooKeeper provides functions such as calculation, storage and the like which can be provided by hardware equipment managed in the cluster to an upper Hadoop distributed file system in an interface mode; the HDFS is a high fault tolerance distributed file system capable of running on general hardware, can provide access data with ultrahigh throughput, and is very suitable for application of large data sets; in a fault big data platform architecture, the HDFS is used for managing all data which can be used for personalized customization, such as various electronic books, video courseware, student access records, examination score analysis, student feedback records and the like; compared with the traditional distributed database, the HDFS has better distributed data coordination capability, and the fault tolerance of the system can be increased through a backup storage technology; the Hadoop provides resource scheduling and management for various application calculations through a uniform resource management framework YARN; the function of the YARN in the framework is to provide uniform resource scheduling service for a plurality of sub-modules in personalized customization and share cluster resources; YARN separates the data resources in the framework from the push mechanism, which has the advantage that HDFS is not affected when the push mechanism of the upper layer changes; when a new data acquisition system appears in the cluster, the push mechanism cannot be completely rewritten due to the addition of new resources.

The upper layer of the YARN is each sub-module program taking Apache Spark as a main computing framework, and digital resource management, student information analysis, personalized push, feedback information collection and the like are all realized on the layer; apache Spark is a distributed computing framework, resources in the HDFS can be read and written at will, and the Apache Spark can be connected with the YARN in a seamless mode; compared with a MapReduce large-scale dataset calculation model carried by Hadoop, Spark is completely calculated based on a memory, and intermediate results are also completely cached in the memory, so that the calculation performance is more excellent, and the processing of a real-time processing system is more efficient. The top layer of the model is an electronic resource cluster deployment, configuration, management tool and a human-computer interface.

In this embodiment, the big data platform can fuse video resources in the network university, electronic books and student feedback information in the electronic library, and mass information in the examination system, and form a virtual resource domain for the personalized customization module on the upper layer, thereby ensuring fast and stable implementation of various accesses to data.

Example 2:

as shown in fig. 1, the embodiment provides a personalized learning system based on a big data platform, and adopts the following technical scheme:

personalized learning system based on big data platform, including: the system comprises a database establishing module, an information interaction module and an information feedback module;

the data establishment module configured to: establishing a big data platform comprising a student information base, a feedback database, a training knowledge base and an interest knowledge resource base, and updating data in the big data platform in real time;

the information interaction module is configured to: inputting culture knowledge into a training knowledge base, and inputting student information, evaluation scores of students and teaching targets into a student information base; a service request is made to a big data platform;

the information feedback module configured to: and according to the service request, the relevant information in the training knowledge base and the interest knowledge resource base is fed back in combination with the evaluation score and the teaching target.

Specifically, the big data platform comprises a ZooKeeper layer, a Hadoop layer and an Apache Spark layer;

the ZooKeeper layer comprises a plurality of data storage devices packaged into a cluster form; the ZooKeeper provides the calculation and storage functions which can be provided by the data storage equipment managed in the cluster to the Hadoop in the form of an interface; the data storage device at least comprises a network university server, a student information server, a digital library and an examination system; specifically, the big data platform fuses video resources on a network university server, electronic books in a digital library, student feedback information in a student information server and test scores in an examination system, and forms a virtual resource domain by means of a personalized customization module;

the Hadoop is used for managing personalized customization data in the big data platform; the personalized customization data at least comprises electronic books, video courseware, student access records, examination score analysis and student feedback records

In this embodiment, Apache Spark is used for the calculation and analysis of data sets in the data platform; and the big data platform acquires knowledge resources interested by the students according to the ID numbers accessed by the students and pushes the learning resources of the related categories to the students for extended learning.

In this embodiment, the database building module is designed as a user layer design; the user layer is an entrance for the student to customize and the administrator to operate, namely a client browser; the student makes a service request to the WEB server through the browser, and returned information is displayed on the browser to complete interaction with the background so as to realize personalized training; the administrator inputs various knowledge and student information related to the cultivation to the background through the browser.

Specifically, in order to embody the characteristics of good openness of a user layer, easy development and maintenance, high portability, strong expandability and the like, a B/S structure is selected to realize the method in the embodiment; the system based on the B/S system structure isolates user service, data service and business service from each other and is divided into three layers; the B/S is a C/S architecture based on a specific communication protocol (HTTP), the B/S architecture is used for meeting the requirements of a thin client and an integrated client, and the final purpose is to save the cost of updating, maintaining and the like of the client and share wide-area resources; based on the above analysis, in this embodiment, the B/S structure is selected as the main structure of the text, Dreamweaver + asp.net 3.5 is used as a client development tool, Microsoft SQL Server 2015 is used as a Server development tool, and a friendly and easy-to-operate student operation interface and a smooth and safe background Server are designed.

In this embodiment, the information interaction module is designed as an application layer; the application layer is a layer for interaction between students and the system and is also a layer which can reflect the value of the whole system most, various functions of the system are realized on the application layer, the application layer comprises a student feedback statistics subsystem, a student customization design subsystem, a student management subsystem, a training knowledge input subsystem and other main modules, and the application layer is a logic realization layer for realizing student customization and management functions.

Specifically, the application layer is an intermediate link and a key link in the embodiment; the layer comprises program modules such as feedback statistics, customized design, student management, knowledge input and the like, and the design mode directly determines the operating efficiency of the system; in the embodiment, the function server is connected with the student client in a LAN +5G mode; the student client mainly comprises mobile equipment, a computer user and virtual reality equipment, so that the computer user and the virtual reality equipment are connected with the function server through the LAN, and the mobile equipment is connected with the function server by adopting a 5G technology; and a program module running on the functional server reads the content of the training knowledge base on the data server through the LAN and feeds the content back to the client.

In this embodiment, the information feedback module is designed as a big data service layer (big data platform); the big data service layer is the bottom layer foundation of the whole platform and provides basic data and real-time data of system operation; the student information base stores information of all cultured students, the feedback database stores culture requirements fed back by the students, the training knowledge base stores teaching links such as training demonstration and operation videos, and data exchange is carried out at any time according to requirements provided by the application layer. In addition, the big data service layer further comprises a network university server, a digital library server and a known network exit node server, knowledge resources which are interested by students can be obtained according to ID numbers accessed by the students, and related types of learning resources are fed back to the customized design module of the application layer so as to be pushed to the students for extended learning.

Specifically, the big data service layer is the bottom layer foundation of the whole platform and provides basic data and real-time data for system operation, and the student information database comprises data such as student numbers, student names, classes, culture delivery units and the like, so that students can conveniently and safely log in at any time to check arrangement conditions needing training; the big data service layer is an important component in system design, and under a specific application environment, a database and an application system thereof are established, so that the database and the application system thereof can effectively store data, provide mapping processing of a data table in a local knowledge base and a business object, comprise various data processing components or services for calling of a business logic layer, shield the difference of specific database access realization technology, and realize access to a bottom system database; the application requirements of various students are met, including feedback requirements and learning requirements.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and those skilled in the art can make various modifications and variations. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present embodiment should be included in the protection scope of the present embodiment.