CN106447558A - guidance of learning method and learning system combining ontology and clustering analysis technology - Google Patents

Abstract

The invention discloses a learning guidance method and system combining ontology and clustering analysis technology. Step 1, course construction; Step 2, user information collection; Step 3, user initial clustering community construction; Step 4, learning plan formulation ; Step 5, user clustering and community building; Step 6, user status and learning plan update; Step 7, course evaluation and resource file update. The invention establishes a user community, organizes discrete students together for learning and communication according to the same characteristics and similar behaviors, and solves the ubiquitous "sense of loneliness" in learning. Including the P2P community self-organization module, which provides users with resource sharing and evaluation interfaces and enriches network teaching resources. Provide personalized course learning plans, and recommend users' target learning knowledge points, target learning resources and learning time according to users' changing data, which improves users' learning quality and learning efficiency.

Description

A Tutoring Method and Learning System Combining Ontology and Cluster Analysis Technology

technical field

The present invention relates to a course guidance method applied to the distance education system, and the system established based on the method, more specifically, relates to a method of creating a course structure by using ontology, and constructing a P2P dynamic community by cluster analysis technology. An interactive course guidance method and a system based on the method.

Background technique

With the continuous development and wide application of computer technology and communication technology, distance education has broken through the physical limitations of traditional teaching, providing more people with rich learning resources and a convenient learning environment. However, most distance education systems currently have problems such as strong sense of loneliness among users, incomplete learning control functions, and disordered learning, which in turn leads to a decline in learning interest, learning quality, and efficiency of a large number of students of different levels. Specific and targeted learning guidance has become an urgent problem to be solved in distance education.

Contents of the invention

Aiming at the deficiencies in the prior art, the purpose of the present invention is to provide a course guidance method combined with ontology and cluster analysis technology and a system based on the method to solve user loneliness, incomplete learning control ability, and disordered learning. And other issues.

In order to achieve the above object, the present invention provides the following technical solution: a teaching method combining ontology and clustering analysis technology, including:

Step 1, curriculum construction: construct curriculum resources with reference to ontology and CELTS standards;

Step 2, user information collection: collect basic information, learning information and interactive behavior information of users;

Step 3, user information analysis: use cluster analysis technology to clean up, filter and analyze the basic information, learning information and interactive behavior information of users collected in step 2, and establish user files and learning initial communities;

Step 4, user clustering and community construction: According to the user profiles established in step 2, the users with the same waiting list are gathered together to build a user community for communication and recommendation between users, and let users conduct community resources Evaluate and generate user feedback values; then use the interaction information between users, resource usage, user feedback values, and user learning real-time to dynamically adjust the community to build a more accurate clustering user community;

Step 5, learning plan formulation: customize a personalized learning plan for users according to the course resources constructed in step 1 and the user profile established in step 3;

Step 6, user status and learning plan update: According to the user's changing behavior and changing profile data, return to step 4 to update the user status and the relationship between users and reconstruct the learning plan until the user completes the course learning;

Step 7, course evaluation and resource file update: When the user completes the course study, generate course evaluation information and suggestions for further study, and update the course resources constructed in step 1 and the relationship between course resources.

As a further improvement of the present invention, the course resource construction in the above step 1 is to divide the course content into different atomic knowledge points, and then establish composite summary knowledge points and context relations for the atomic knowledge points, and hang the course learning resources under the atomic knowledge points Click on knowledge.

As a further improvement of the present invention, the context relationship includes an inclusion relationship and a pre-knowledge relationship, and there is a transitivity between the inclusion relationship and the pre-knowledge relationship.

As a further improvement of the present invention, the content of the learning plan in the above step 4 is the arrangement of learning time and course resources and the recommendation of learning objects.

As a further improvement of the present invention, the user community in step 4 is to classify users with similar interests and similar behaviors through cluster analysis technology, and users communicate, learn and recommend course resources in the user community.

As a further improvement of the present invention, the dynamic adjustment of the user community in step 4 is based on comparing the feedback value of the user community with the preset expected value of the user community, and adjusting according to the comparison result.

As a further improvement of the present invention, the formula for comparing the user feedback value in step 4 with the expected value of the preset user community is:

Among them, Score represents the feedback value of the user to the user community, and ExpectedScore represents the expected value of the user community. When is a positive response; if zero response; otherwise, negative response.

As a further improvement of the present invention, the content of the learning plan in the fifth step above is the recommendation of knowledge points and the arrangement of course resources and learning time.

A system for applying the above method provided by the present invention includes:

User terminal: a port for user learning and communication;

Administrator terminal: a port for administrators to maintain the system;

The course ontology building module, coupled to the administrator terminal, is used to build course resources and continuously update course resources;

User data collection module: coupled to the user terminal and the course ontology building module, used to collect the user's basic information, learning information and interactive behavior information;

User cluster analysis module: coupled to the user data collection module, use cluster analysis technology to clean up, filter and analyze the collected user basic information, learning information and interactive behavior information, establish user files, and build user communities;

P2P community self-organization module: coupled with the user clustering analysis module, user data collection module and course ontology construction module, based on the user community, organize various user communities to communicate and learn from each other, and dynamically build the community according to the real-time feedback data of users;

Learning plan generation module: coupled with the course ontology building module and the P2P community self-organization module, it is used to customize the user's personalized learning plan and continuously update the learning plan.

As a further improvement of the present invention, the community management module is used to manage the interaction between users in the community;

User communication module, used for mutual communication between users;

Resource recommendation module, used for resource recommendation among users;

A learning and assessment module for learning within the community and measuring results;

The community adjustment module is used to adjust the member structure of the user community;

The community management module, user communication module, resource recommendation module, learning and evaluation module and community adjustment module are mutually connected in parallel.

The beneficial effect of the present invention is to establish a user community, organize discrete students to study and communicate according to the same characteristics and similar behaviors, and solve the ubiquitous "loneliness" in learning. Using clustering analysis technology, it provides a new method for user feature collection and division, and the complexity of the algorithm is low. Including the P2P community self-organization module, providing users with resource sharing and evaluation interfaces, dynamically updating and enriching network teaching resources. Provide a personalized course learning plan, and recommend the user's target learning knowledge points, target learning objects and learning time according to the user's changing data, which improves the learning quality and learning efficiency of students.

Description of drawings

Fig. 1 is a kind of flow chart of the teaching method combining ontology and clustering analysis technology;

Figure 2 is a structural diagram of the functional modules of the system.

detailed description

The present invention will be described in further detail below in conjunction with the embodiments given in the accompanying drawings.

Referring to Fig. 1, a teaching method combining ontology and clustering analysis technology in this embodiment includes

Step 1, curriculum construction: construct curriculum resources with reference to ontology and CELTS standards;

Specifically: analyze the course content with the guidance of ontology, and divide the course content into atomic knowledge points. Then according to the different functions of different atomic knowledge points in the learning process, establish mutual relations for atomic knowledge points. The relationship between atomic knowledge points includes inclusion relationship and pre-knowledge relationship, where b contains a, which is represented by the relationship a<p, b>p, and the relationship weight between a and b represents the degree of membership between a and b; The pre-knowledge relationship means that d must be mastered before mastering c, and the relationship weight between c and d indicates the degree of contribution of c relative to mastering d. Dividing the relationship between atomic knowledge points in this way makes it easier to clarify the relationship between atomic knowledge points and facilitate the customization of later learning plans. The transitivity of inclusion relationship is expressed as a<p, p<x, x<b, that is, there is an implicit inclusion relationship between different knowledge points. Composite knowledge points are the fusion of atomic knowledge points in the same field, which serve as a navigation function and index the course content, so that users can understand and learn course knowledge in related fields.

Step 2, user information collection: collect basic information, learning information and interactive behavior information of users;

Specifically: the user needs to register an account and fill in the relevant basic information when logging in at the user terminal. The basic information includes age, education, learning courses, and learning time periods, etc. The user data collection module collects this information through the user terminal; Learning information and interactive behavior information generated in each module of the system.

Step 3, user information analysis: use cluster analysis technology to clean up, filter and analyze the basic information, learning information and interactive behavior information of users collected in step 2, and establish user files and learning initial communities;

Specifically: classify and divide users’ basic information, learning information, and interactive behavior information based on different dimensions. The classification principle is to mark several features for the user groups with the highest similarity between users according to the similarity between users, and establish User profiles and learning starter community.

Step 4, user clustering and community construction: According to the user profiles established in step 2, the users with the same waiting list are gathered together to build a user community for communication and recommendation between users, and let users conduct community resources Evaluate and generate user feedback values; then use interaction information between users, resource usage, user feedback values, and user learning real-time to dynamically adjust the community to build a more accurate clustering user community; help users learn and communicate better, Reduce the "loneliness" in the learning process, increase users' interest in learning, and enable users to master relevant knowledge better and faster.

Specifically: the dynamic adjustment of the user community is mainly adjusted according to the user's evaluation of the user community. First define a threshold, and then compare the user's feedback value with the threshold to determine the direction of the community's response. When the response is positive, it means that the community is suitable for users; when it is negative, it means that the community is not suitable for users and needs to be adjusted. Its relationship is:

Among them, Score represents the user's feedback value on the item, and ExpectedScore represents the expected value of the system. When is a positive response; if zero response; otherwise, negative response. This adjustment method is simple and easy, so that the user can obtain a better experience in use.

Step 5, learning plan formulation: customize a personalized learning plan for users according to the course resources constructed in step 1 and the user profile established in step 3;

Specifically: the generation of the learning plan is to find the target atomic knowledge points based on the user profile, and then arrange the learning duration and learning course resources according to the user's learning process of the relevant atomic knowledge points, and recommend high-scoring users with relevant knowledge for learning. object. Customize personalized learning plans for users, ensure the feasibility of the plans, guide users to learn according to the plans, and improve users' learning efficiency.

Step 6, user status and learning plan update: According to the user’s changing behavior and changing profile data, return to step 4 to update the user status and the relationship between users and reconstruct the learning plan until the user completes the course learning; through continuous adjustment , provide a personalized learning plan that is more suitable for users, guide users to learn, enable users to learn continuously according to the plan, and finally master relevant knowledge.

Step 7, course evaluation and resource file update: when the user completes the course study, generate course evaluation information and suggestions for further study, and update the relationship between the resource library and resources. Continuously improve the curriculum system to make the relationship between knowledge points more clear and help more users learn the corresponding knowledge better.

As shown in Figure 2, a system applying the above method in this embodiment:

include

User terminal: a port for user learning and communication;

Administrator terminal: a port for administrators to maintain the system;

The course ontology building module 301, coupled to the administrator terminal, is used to establish the structure of knowledge points, create and manage course resources;

User data collection module 302: coupled to the user terminal and the course ontology building module, used to collect the user's basic information, learning information and interactive behavior information;

User clustering analysis module 303: coupled to the user data collection module, using clustering analysis technology to clean up, filter and analyze the collected user basic information, learning information and interactive behavior information, establish user files, and construct user initial clustering ;

P2P community self-organization module 304: coupled to the user clustering analysis module, user data collection module and course ontology building module, based on the user community organization of various user communities to communicate with each other, and according to user communication and learning behavior, user real-time feedback data, Dynamically build and adjust the community;

Learning plan generating module 305: coupled to the course ontology building module and the P2P community self-organizing module, used to customize the user's personalized learning plan and continuously update the learning plan.

Modular design system reduces program complexity and simplifies program design, debugging and maintenance. The user logs into the learning system through the service terminal, enters the user's basic information, and completes the preliminary evaluation of the course. The user terminal includes a mobile phone port and a PC port. Users conduct learning, interaction, evaluation and P2P communication activities on the user terminal. The information of the user terminal is sent to the user data collection module 302 through the Internet. User initial information collected by the user data collection module 302. The user cluster analysis module 303 uses cluster analysis technology to analyze information, establishes user files, and gathers users with similar characteristics to establish a user community. The learning plan generation module 305 combines user files and historical data to generate personalized learning plan to guide the user's learning behavior. The P2P community self-organization module 304 dynamically builds the community according to the user's communication and learning situation and feedback information in the community.

As an improved specific implementation, the P2P community self-organization module 304 includes

Community management module, used to manage the interaction between users in the community;

User communication module, used for mutual communication between users;

Resource recommendation module, used for resource recommendation among users;

A learning and assessment module for learning within the community and measuring results;

The community adjustment module is used to adjust the member structure of the user community;

The community management module, user communication module, resource recommendation module, learning and evaluation module and community adjustment module are mutually connected in parallel. Through the cooperative operation of each module, the operation of the P2P community self-organization module 304 is smoother, so that the user can obtain a better interactive experience.

To sum up, the present invention provides a learning guidance method that not only efficiently completes course learning but also improves user experience, provides communication channels for users, and is suitable for distance education of various courses.

The above descriptions are only preferred implementations of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions under the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those skilled in the art, some improvements and modifications without departing from the principles of the present invention should also be regarded as the protection scope of the present invention.

Claims (9)

1. A teaching method combining ontology and cluster analysis technology, including: Step 1, curriculum construction: construct curriculum resources with reference to ontology and CELTS standards; Step 2, user information collection: collect basic information, learning information and interactive behavior information of users; Step 3, user information analysis: use cluster analysis technology to clean up, filter and analyze the basic information, learning information and interactive behavior information of users collected in step 2, and establish user files and learning initial communities; Step 4, user clustering and community construction: According to the user profiles established in step 2, the users with the same waiting list are gathered together to build a user community for communication and recommendation between users, and let users conduct community resources Evaluate and generate user feedback values; then use the interaction information between users, resource usage, user feedback values, and user learning real-time to dynamically adjust the community to build a more accurate clustering user community; Step 5, learning plan formulation: customize a personalized learning plan for users according to the course resources constructed in step 1 and the user profile established in step 3; Step 6, user status and learning plan update: According to the user's changing behavior and changing profile data, return to step 4 to update the user status and the relationship between users and reconstruct the learning plan until the user completes the course study; Step 7, course evaluation and resource file update: When the user completes the course study, generate course evaluation information and suggestions for further study, and update the course resources constructed in step 1 and the relationship between course resources. 2. A kind of guidance method combining ontology and cluster analysis technology according to claim 1, characterized in that: the course resource construction in the above step 1 is to divide the course content into different atomic knowledge points, and then Atomic knowledge points establish composite summary knowledge points and contextual relationships, and link course learning resources under atomic knowledge points. 3. A teaching method combining ontology and clustering analysis technology according to claim 2, characterized in that: the contextual relationship includes an inclusion relationship and a pre-knowledge relationship, and the relationship between the inclusion relationship and the pre-knowledge relationship is transitive. 4. According to claim 1 or 2 or 3, the teaching method combining ontology and clustering analysis technology is characterized in that: the user community in the step 4 is a group of users with similar interests and similar behaviors through aggregation Classification by category analysis technology, users communicate, learn and recommend course resources in the user community. 5. The learning guidance method combining ontology and clustering analysis technology according to claim 4, characterized in that: the dynamic adjustment of the user community in the step 4 is based on the feedback value of the user to the user community and the preset user community The community's expected value is compared and adjusted according to the comparison result. 6. The teaching method combining ontology and cluster analysis technology according to claim 5, characterized in that: the formula for comparing the user feedback value in the step 4 with the expected value of the preset user community is $<span\; class="notranslate">\; \&part;</span><span\; class="notranslate">\; =</span>\left\{\begin{array}{cc}\mathrm{<span\; class="notranslate">\; 1</span>}& \mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; x</span>}\mathrm{<span\; class="notranslate">\; p</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; ></span>\mathrm{<span\; class="notranslate">\; 0</span>}\\ \mathrm{<span\; class="notranslate">\; 0</span>}& \mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; x</span>}\mathrm{<span\; class="notranslate">\; p</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0</span>}\\ <span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}& \mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; x</span>}\mathrm{<span\; class="notranslate">\; p</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; t</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; d</span>}\mathrm{<span\; class="notranslate">\; S</span>}\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; r</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; <</span>\mathrm{<span\; class="notranslate">\; 0</span>}\end{array}\right.$ Among them, Score represents the feedback value of the user to the user community, and ExpectedScore represents the expected value of the user community. When is a positive response; if zero response; otherwise, negative response. 7. The learning guidance method combining ontology and cluster analysis technology according to claim 4, characterized in that: the content of the learning plan in the above step five is the recommendation of knowledge points and the arrangement of course resources and learning time. 8. A system for applying the method according to any one of claims 1 to 7, characterized in that: comprising User terminal: a port for user learning and communication; Administrator terminal: a port for administrators to maintain the system; The course ontology building module (301), coupled to the administrator terminal, is used to build course resources and continuously update course resources; User data collection module (302): coupled to the user terminal and the course ontology building module, used to collect the user's basic information, learning information and interactive behavior information; User clustering analysis module (303): coupled to the user data collection module, using clustering analysis technology to clean up, filter and analyze the collected user basic information, learning information and interactive behavior information, establish user files, and build user communities ; P2P community self-organization module (304): coupled to the user cluster analysis module, user data collection module and course ontology building module, based on the user community, organize various user communities to communicate and learn from each other, and dynamically build the community according to the real-time feedback data of users ; Learning plan generating module (305): coupled to the course ontology building module and the P2P community self-organizing module, used to customize the user's personalized learning plan and continuously update the learning plan. 9. A kind of intelligent learning system according to claim 8, characterized in that: said P2P community self-organization module includes Community management module, used to manage the interaction between users in the community; User communication module, used for mutual communication between users; Resource recommendation module, used for resource recommendation among users; A learning and assessment module for learning within the community and measuring results; The community adjustment module is used to adjust the member structure of the user community; The community management module, user communication module, resource recommendation module, learning and evaluation module and community adjustment module are mutually connected in parallel.