Skip to content
【Pinned】【Experience a Complete and Happy Educational Life】
【Guarding New Education, Guarding Truth, Goodness, and Beauty】
Educational Knowledge Graphs
Common Application Scenarios and Logic
Author｜Anonymous Truth, Goodness, and Beauty
Source｜Information Technology Education for Primary and Secondary Schools
01
Introduction to Knowledge Graphs
A knowledge graph is a large-scale semantic network, a semantic representation of the real world. It represents entities as nodes, and the attributes of entities and relationships between entities as edges, forming a network structure. This structured format is recognizable by humans and friendly to machines, facilitating machine understanding. The large-scale concepts, attributes, and relationships in the graph provide rich semantic information and associations, naturally possessing various characteristics of graphs, allowing related operations and applications. Once constructed, it can also serve as background knowledge for downstream applications. The knowledge graph was initially proposed by Google, primarily to improve the capabilities of search engines and enhance search quality. Its unique features enable it to play an important role in various aspects of artificial intelligence.
Construction of Subject Knowledge Graphs in Education
The construction of knowledge graphs is typically application-oriented; before constructing a graph, one must clarify the problems to be solved and the knowledge required to address these problems, and then design the ontology of the knowledge graph to cover this knowledge. First, let’s introduce some common application scenarios and logic of educational knowledge graphs, design the ontology of educational graphs based on these applications, and then further construct the knowledge graph.
(1) Application Logic of Educational Knowledge Graphs
The educational knowledge graph, centered around subject knowledge, establishes hierarchical relationships among knowledge points in various subjects, the associations between knowledge points, and the sequential relationships between different knowledge points, forming a subject knowledge graph. Using this graph, the relationships between knowledge points can be visually displayed to students, making it clear and intuitive, aiding students in building a knowledge system, referencing key points, discovering connections between knowledge points, and helping students summarize and eliminate knowledge blind spots.
After constructing the subject knowledge graph, it can be associated with teaching resources (textbooks, exam questions, handouts, teaching videos, test papers, etc.), and through user information and learning records, establish associations between knowledge points and users. The knowledge graph can more accurately depict students’ knowledge mastery and resources, enabling precise assessments of user learning situations, learning path planning, and personalized recommendations of learning resources.
It can also help teachers better understand students’ learning situations, optimize teaching methods, and adjust teaching strategies. By associating with teaching research materials, it can actively recommend teaching research to enhance the efficiency and quality of teachers’ lesson preparation. A teaching assistance Q&A system based on knowledge graph question-answering technology can effectively reduce the burden of simple repetitive questions on teachers and greatly satisfy students’ inquiry needs.
(2) Education Knowledge Resource Construction Centered on Subject Knowledge Graphs
The construction of educational knowledge resources centered on knowledge graphs utilizes knowledge graphs to establish associations between domain knowledge, linking knowledge points with various educational resources such as different versions of textbooks, teaching aids, handouts, videos, and exam questions, forming an overall network. These association networks support upper-level applications.
In the subject knowledge graph of the education field, the relationships between knowledge mainly include: hierarchical relationships, primarily between parent and child concepts, and between concepts and entities. Conceptual graphs express the relationships between concepts in the education field. There are many conceptual contents in the education field, and these relationships form the thread of knowledge. Containment relationships, specific sub-topics under knowledge points, and the whole-part relationship. Sequential relationships can be used for learning planning. In different subjects, there are also some special relationships, such as mutual exclusion and causation, which require collaboration between domain experts and knowledge engineers to refine during the actual construction of graph resources.
Knowledge in educational graphs also has rich attributes, such as common attributes like “exam points,” “difficult points,” “common mistakes,” and “exam syllabus requirements.” Different subjects have specific fine-grained attributes, such as “definition,” “properties,” “area formula,” and “perimeter formula” in mathematics.
Application of Knowledge Graphs in Smart Education
(1) Precision Profiling Based on Educational Knowledge Graphs
Precision profiling based on educational graphs extracts key information by analyzing user behavior and its connections with various resource objects to characterize users. User profiles based on knowledge graphs can enhance user profiling data, making the characterization of users more comprehensive and accurate.
1. Precision User Profiling
User profiling technology should be familiar to everyone; it aims to better characterize users for understanding them, essentially “tagging” them. The accuracy of user profiling determines how accurately we understand users. In practical applications, there are two main issues to resolve: the first is incomplete profiling data, and the second is incorrect profiling data.
To address these issues, knowledge graphs can be utilized. The nodes in knowledge graphs represent abstractions of domain knowledge in education, covering a sufficient number of entities and concepts, serving as a source of tags for user profiles. The high quality of these tags makes them more accurate. These tags are interrelated, and the graph contains rich semantic relationships, helping machines understand the meanings of these tags. The friendly structure facilitates better human understanding and allows for intuitive discovery of relationships between tags. Algorithms such as tag propagation and cross-domain recommendations can be used to mine more precise tags to describe users, enriching user tags and enhancing accuracy. Additionally, during user profiling, user profiles can be presented as standalone visual products, generating personalized and dynamically changing user knowledge graphs based on the relationships in the graph.
2. Precision Learning Situation Analysis
Knowledge graphs can facilitate more precise learning situation analysis. Traditional educational experts (teachers’ experience) rely on experience to assess learners’ knowledge and ability states, lacking the integration of educational measurement concepts, leading to significant randomness and subjectivity. By leveraging knowledge graphs and big data analysis methods, the objective learning processes of learners can be mined from multiple dimensions, allowing for analysis that encompasses various factors, not limited to test scores, error logs, and learning records to assess knowledge mastery and weak knowledge, as well as deeper learning speed, learning preferences, and cognitive levels. This results in more personalized and objective analysis outcomes.
For unmet learning objectives, knowledge graphs can perform cause analysis, identifying weak points and associated knowledge points, effectively filling knowledge gaps. The diagnostic process possesses better adaptability and personalization.
(2) Enhancing Teaching Quality and Efficiency
Knowledge graphs in assistive teaching applications help teachers with lesson preparation, teaching research, question generation, and exam analysis. The system can recommend related materials (lesson plans, course explanations, assignments, etc.) to enhance teachers’ teaching efficiency, and graph-based searches can return the required content more accurately.
1. Intelligent Lesson Preparation
Utilizing subject knowledge graphs to link subject knowledge points with textbooks, handouts, exercises, etc., based on teachers’ teaching progress and textbook versions, continuously pushes suitable lesson preparation resources that meet teaching needs, allowing teachers to quickly and accurately obtain the resources they need, enhancing lesson preparation efficiency and quality. In addition to lesson preparation, subject knowledge graphs can also assist in intelligent exam generation and exam analysis, significantly improving teaching research efficiency.
Through precise analysis of learning situations, the system recommends related consolidation exercises, devises targeted teaching strategies, and enhances the specificity of teaching through precision teaching.
Before, during, and after class, data mining and intelligent capabilities are comprehensively utilized. Before class, data mining techniques are used to obtain student learning situation data, formulating teaching strategies to make decisions data-driven. During class, the established teaching strategies are applied for targeted teaching, explaining knowledge points, and conducting group discussions. The knowledge graph visualizes the inherent relationships of knowledge, helping students build a deep understanding of knowledge. After class, related exercises are recommended based on students’ learning situation and abilities, providing personalized consolidation exercises for errors. This improves the quality and specificity of classroom teaching, integrating dynamic data analysis and dynamic learning situation diagnosis throughout the teaching process, achieving tailored instruction and making teaching decisions data-driven and intelligent.
Deep reading based on knowledge graphs aims to achieve an intelligent and comprehensive understanding of the relationships between knowledge. Utilizing entity linking technology, electronic publications can be recognized and connected, displaying current knowledge information in the form of knowledge cards. It can also relate to other associated knowledge and recommend relevant knowledge, helping users connect knowledge together. This greatly promotes users’ comprehensive understanding of knowledge. Deep reading can be applied not only in education but also in knowledge management and the publishing industry.
The core technology underlying deep reading is entity linking technology. Currently, the entity understanding service developed by our knowledge workshop allows machines to comprehend entities in text, making entity search and semantic search possible, achieving over 90% accuracy and recall in general domains.
Education robots have become an important application in the education field. Utilizing education robots centered around question-answering systems can achieve course Q&A, knowledge retrieval recommendations, teaching management, and other teaching tasks. This not only alleviates teachers’ burdens and pressures but also addresses students’ practical issues. An excellent and comprehensive teaching robot integrates multiple system modules, including task-oriented Q&A, chatbots, knowledge-based Q&A, and search recommendation systems, while possessing multi-turn Q&A capabilities. Knowledge graphs play an important role in understanding query questions and generating language guided by knowledge, being core to KBQA.
Evolution Path of Education Intelligence Centered on Knowledge Graphs
Knowledge graphs are increasingly taking on the mission of aiding the intelligence of the industry. Therefore, exploring the evolution path of industry intelligence based on knowledge graphs is crucial. After years of practice, this path is becoming clearer, presenting a model of iterative development between knowledge resource construction and knowledge application. The basic principles for implementation are overall planning, application-driven, and promoting construction through use. The iterative development path of knowledge resource construction and knowledge application.
(1) Application-Driven, Promoting Construction through Use
The implementation of intelligence in the education industry must follow the implementation plans of general industries, being application-oriented. The education application scenarios are numerous; overall planning is required, gradually implementing according to current business development needs and data, and selecting suitable application scenarios. In specific applications, the ability to construct graphs should be developed, directly generating business value. One should not blindly construct graphs without specific business outlets for support, as this would merely serve as a technical capability reserve. Unless it is a leading enterprise’s AI Lab that does not pursue short-term monetization, it is difficult to gain sufficient internal support. Only when specific business value is generated can there be enough motivation to promote the long-term and steady development of projects centered on intelligent transformation based on graphs.
(2) Iterative Development
In the intelligent implementation of knowledge graphs in the education industry (and similarly in vertical industries), compared to knowledge application, knowledge acquisition and resource construction are greater bottlenecks. Knowledge resource construction is a long-term task; it cannot be accomplished overnight and must be steadily advanced, accumulating knowledge bases without shortcuts. An iterative spiral development model should be adopted.
In each iteration cycle, it is essential to grasp the principle of moderation, prioritize application scenarios with expected better outcomes, and reasonably control the boundaries and scale of knowledge, constructing knowledge resources centered on knowledge graphs and conducting corresponding knowledge applications. Feedback from internal and external users should be utilized to improve corresponding applications and knowledge resource construction. Once specific applications show initial effectiveness, the focus can gradually expand from limited applications to more application scenarios and build more knowledge resources. This entire process continues iterating until comprehensive intelligence is achieved.
Cognitive intelligence is the key to advanced artificial intelligence, and its realization relies on knowledge graphs. Nowadays, there are more and more intelligent applications based on knowledge graphs in vertical industries. Many application scenarios in the education field have shown good results. However, cognitive intelligence and its application in education are still in the developmental stage, with many areas needing improvement. For instance, in graph construction, the educational knowledge graph clearly requires multimodal knowledge graphs; the complexity of knowledge in the education field increases the difficulty of segmenting knowledge points, and the richness of relationships between knowledge points also requires continuous optimization. Overall, the application of knowledge graphs in educational intelligence has a significant role and a bright future. It is believed that with further technological maturity, national policy support, continuous capital investment, and ongoing innovation by commercial companies, educational intelligence will achieve remarkable results in the coming years.
Content Source | Hexi University, Higher Education Innovation 100 People WeChat Public Account
“Nobel Prize in Education”—Why Zhu Yongxin and New Education Experiment?
China Education News: “New Education Experiment”—What has it brought to teachers?—A clear growth path for teachers, making their growth visible!
How to Create a Book Fragrant Campus?—Without a campus filled with the fragrance of books, there is no true school.
Cheng Jieming: What I See from Zhu Yongxin’s “New Education”—Creating a Complete and Happy Educational Life.
Zhu Yongxin: The “Long March” of the New Education Experiment, Writing Papers on the Land of the Motherland.
Learn and Join the Latest Guidelines of New Education｜China Tao Xingzhi Research Association New Education Branch: Notice on the Development of Group Members and Individual Members.
Share the beauty, salute the original! 【Guarding New Education】, guarding truth, goodness, and beauty! Let’s meet in truth, goodness, and beauty, 【Guarding New Education】!
“The Catcher in the Rye” has a term, guarding. Education is neither management nor neglect; between management and neglect, there is a term called “guarding.”——Chen Dongqiang
Every day is new, and every day is new, and again new. The new day is called great virtue. Only those who advance can be called new.The way is in the daily renewal. Virtue is precious in daily renewal. Always new, self-renewing, completely new. Daily renewal without end, looking like the dawn.——Daily Renewal Collection
Believe in seeds, believe in time. Plant seeds, day by day, year by year; guard the years, quietly waiting for flowers to bloom.——Chen Dongqiang
【Guarding New Education】, guarding truth, goodness, and beauty!Helping teachers and studentsexperience a complete and happy educational life. 【Guarding New Education】: Listening to the educational wisdom of masters, sharing the educational insights of wise men, gathering creative education from the fields, and supporting the educational dreams of peers. 【Guarding New Education】: Presenting the beauty of humanity, fostering the beauty of others.
New education experiment,is an education experiment that starts with the professional development of teachers, aiming to help members of the new education community live a complete and happy educational life through ten actions: “creating a book fragrant campus, co-writing essays with teachers and students, listening to outside voices, cultivating excellent eloquence, building ideal classrooms, constructing digital communities, promoting one monthly event, creating perfect classrooms, developing excellent courses, and collaborating with families to build together.”
Where is the newness of new education?For me, when some ideas are gradually forgotten and then brought up again, it is new; when some ideas are only spoken by others and now acted upon, it is new; when some ideas evolve from vagueness to clarity, from scarcity to richness, it is new; when some ideas are inherited, promoted, and innovated in a new context, it is new.
