Applications of Knowledge Graphs in Intelligent Education

Introduction to Knowledge Graphs

A knowledge graph is a large-scale semantic network that represents the real world in a semantic format. It represents entities as nodes, and the properties of entities and the relationships between entities as edges, forming a network structure. This structured form is recognizable by humans and friendly to machines, facilitating machine understanding. The large-scale concepts, attributes, and relationships between entities in the graph provide rich semantic information and associations, inherently possessing various characteristics of graphs, enabling relevant operations and applications. Once constructed, it can also serve as background knowledge for downstream applications. Initially proposed by Google, the knowledge graph was primarily used to improve the capabilities of search engines and enhance search quality. Due to its unique characteristics, the knowledge graph plays an important role in various aspects of artificial intelligence.

Applications of Knowledge Graphs in Intelligent Education

Construction of Subject Knowledge Graphs in Education

The construction of knowledge graphs is typically application-oriented. Before constructing a graph, it is essential to 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 the educational graph based on these applications, and then further construct the knowledge graph.

(1) Application Logic of Educational Knowledge Graphs

The educational knowledge graph centers around subject knowledge, establishing hierarchical relationships between knowledge points of various subjects, the connections between knowledge points, and the sequential relationships between different knowledge points, forming a subject knowledge graph. This graph can visually display the relationships between knowledge points to students, making it clear and intuitive, and can naturally help students construct a knowledge system, reference key knowledge points, discover associations between knowledge points, and assist students in summarizing and eliminating 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 connections between knowledge points and users. Utilizing the knowledge graph allows for a more precise characterization of students’ knowledge mastery and a more accurate depiction of resources. This enables precise academic assessments of users, learning path planning, and personalized recommendations for learning resources.

It can also help teachers better understand students’ academic situations, optimize teaching methods, and adjust teaching strategies. By associating with teaching research materials, proactively recommending teaching research can enhance the efficiency and quality of teachers’ preparation. A teaching assistance system centered around knowledge graph Q&A can effectively reduce the burden of repetitive questions on teachers and greatly meet students’ inquiry needs.

(2) Construction of Educational Knowledge Resources Based on Subject Knowledge Graphs

The construction of educational knowledge resources centered on knowledge graphs establishes associations between domain knowledge, linking knowledge points with various educational resources such as different versions of textbooks, teaching aids, handouts, videos, and exam questions to form a comprehensive 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. The concept graph expresses the relationships between concepts in the education field. There are many conceptual contents in the education field, and the relationships between these concepts form the entire knowledge framework. Inclusion relationships refer to specific sub-topics under a knowledge point, representing the whole and parts. Sequential relationships can be used for learning planning. In different subjects, there are also some special relationships, such as mutual exclusivity and causality, which need to be refined and clarified by domain experts and knowledge engineers 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.

Applications of Knowledge Graphs in Smart Education

(1) Precision User Profiling Based on Educational Knowledge Graphs

Precision user profiling based on educational graphs extracts key information from user behavior data and their connections with various resource objects to characterize users. User profiles based on knowledge graphs can enhance the data of user profiles, providing a more comprehensive and precise characterization of users.

1. Precision User Profiles

User profiling technology should be quite familiar by now, as it aims to better characterize users for understanding them, essentially “tagging” them. The accuracy of user profiles determines how accurately users can be understood. In practical applications, two main issues need to be addressed: the first is incomplete profile data, and the second is incorrect profile data.

To address these issues, knowledge graphs can be utilized. The nodes in knowledge graphs abstract the knowledge of the education field, covering a sufficient number of entities and concepts, serving as a source of tags for user profiles. The high quality of these tags ensures their accuracy. These tags are interconnected, and the graph contains rich semantic relationships, helping machines understand the meanings of these tags. The user-friendly structure facilitates better human understanding and the 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 user accuracy. Additionally, when creating user profiles, they can be visualized as products, generating personalized, dynamically changing user knowledge graphs using the relationships in the graph.

2. Precision Academic Situation Analysis

Knowledge graphs can enable more precise analysis of academic situations. Traditional educational experts (teachers’ experiences) rely heavily on experience to assess learners’ knowledge and ability statuses, lacking the integration of educational measurement concepts, which results in significant randomness and subjectivity. Using knowledge graphs and big data analysis methods can objectively mine learners’ learning processes from multiple dimensions. The data can be mined from various dimensions, not limited to test scores, error logs, and learning records, revealing knowledge mastery and weak knowledge as explicit features. It can also extract deeper learning speeds, learning preferences, cognitive levels, and other implicit features, making the analysis results more personalized and objective.

For unmet learning objectives, knowledge graphs can be used for root cause analysis, identifying weak points and related knowledge points, effectively filling gaps in knowledge. The diagnostic process is more adaptive and personalized.

(2) Enhancing Teaching Quality and Efficiency

Knowledge graphs in assisted teaching applications help teachers with lesson preparation, teaching research, question creation, and exam analysis. The system can recommend similar related materials (lesson plans, course explanations, assignments, etc.) to improve teachers’ teaching efficiency, and graph-based searches can return the required content more accurately.

1. Intelligent Lesson Preparation

By utilizing subject knowledge graphs, the system links subject knowledge points with textbooks, handouts, exercises, etc., and continuously pushes suitable lesson preparation resources based on teachers’ teaching progress and textbook versions, allowing for quick and accurate retrieval of required resources to enhance lesson preparation efficiency and quality. In addition to lesson preparation, subject knowledge graphs can also assist in intelligent question creation and exam analysis.

2. Smart Classrooms

Through precise analysis of academic situations, the system recommends relevant consolidation exercises, formulates targeted teaching strategies, enhances teaching relevance, and implements precise teaching. Before, during, and after class, data mining and intelligent capabilities are comprehensively applied. Before class, data mining techniques are used to obtain students’ academic data to formulate teaching strategies, making decision-making data-driven. During class, teaching strategies are implemented for targeted instruction, explaining knowledge points, and conducting group discussions. Utilizing knowledge graphs to visualize the inherent connections of knowledge helps students build a deeper understanding of knowledge. After class, relevant exercises are recommended based on students’ academic conditions and learning abilities, providing personalized and targeted practice exercises to consolidate mistakes, enhancing the quality and relevance of classroom teaching. Dynamic data analysis and academic situation diagnostics run throughout the entire teaching process, achieving tailored instruction and making teaching decisions data-driven and intelligent.

(3) Deep Reading

Deep reading based on knowledge graphs aims to achieve an intelligent and comprehensive understanding of the relationships between knowledge. Using entity linking technology, electronic publications can be identified and connected to entities, displaying current knowledge information in the form of knowledge cards. It can also link to other related knowledge and recommend relevant knowledge, helping users connect knowledge. This greatly promotes users’ comprehensive understanding of knowledge. Deep reading can be applied not only in the education field but also in knowledge management and publishing industries. The core technology relied upon for deep reading is entity linking technology. Currently, our knowledge factory has developed entity understanding services that allow machines to comprehend entities in text, making entity search and semantic search possible, achieving over 90% accuracy and recall rates in general domains.

(4) Q&A Robots

Educational robots have become an important application in the education field. Utilizing education robots centered around Q&A systems can facilitate course Q&A, knowledge retrieval recommendations, teaching management, and other related teaching tasks. This not only alleviates teachers’ burdens and stress but also addresses students’ practical problems. An excellent comprehensive teaching robot integrates task-oriented Q&A, chatbots, knowledge-based Q&A, search recommendation systems, and other system modules, while possessing multi-turn Q&A capabilities. Knowledge graphs play a vital role in understanding query questions and generating language guided by knowledge, serving as the core of KBQA.

The Evolution Path of Education Intelligence Centered on Knowledge Graphs

Knowledge graphs are increasingly taking on the mission of assisting the intelligentization of industries. Exploring the evolution path of industry intelligentization based on knowledge graphs is therefore crucial. After years of practice, this path has become clearer, presenting an iterative development model of knowledge resource construction and knowledge application. The fundamental principles for implementation are: overall planning, application-driven, and promoting construction through application. The iterative development path of knowledge resource construction and knowledge application.

(1) Application-Driven and Promoting Construction through Application

The intelligentization of the education industry must follow the implementation plans of general industries, focusing on applications. The education application scenarios are numerous and require overall planning for gradual implementation. Based on the current business development needs and data and technical foundations of enterprises, suitable application scenarios should be selected to build graph capabilities in specific applications while directly generating business value. It is not feasible to blindly create graphs without specific business outlets for support; unless it is a leading enterprise’s AiLab that does not pursue short-term monetization, it is challenging to gain sufficient internal support. Only when concrete business value is generated can there be enough motivation to promote the long-term, steady development of intelligent transformation projects centered around knowledge graphs.

(2) Iterative Development

In the intelligent implementation of knowledge graphs in the education industry (and similarly in vertical industries), the acquisition of knowledge and the construction of knowledge resources are greater bottlenecks compared to knowledge application. The construction of knowledge resources is a long-term endeavor that cannot be accomplished overnight; it requires solid progress in knowledge resource construction and the accumulation of knowledge bases with no shortcuts. An iterative spiral development model should be adopted, starting from points and expanding outward.

In each iteration cycle, the principle of moderation should be adhered to, prioritizing application scenarios with better expected outcomes, reasonably controlling the boundaries and volume of knowledge, constructing knowledge resources centered around knowledge graphs, and developing corresponding knowledge applications. Based on feedback from internal and external users, the relevant applications and knowledge resource construction can be refined. Once specific applications show initial results, the scope can gradually expand from limited applications to more scenarios and build more knowledge resources. The entire process continues to iterate until comprehensive intelligentization is achieved.

Cognitive intelligence is key to advanced artificial intelligence, and its realization relies on knowledge graphs. Nowadays, there are increasingly 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 the education field are still in the development stage, with many areas needing improvement. For instance, in graph construction, the demand for multimodal knowledge graphs is evident, and the complexity of knowledge in the education field increases the difficulty of segmenting knowledge points, while the richness of relationships between knowledge points also needs continuous optimization. Overall, the application of knowledge graphs in educational intelligence is significant, with bright prospects. It is believed that with further technological maturity, support from national policies, continuous capital investment, and ongoing innovation from commercial companies, educational intelligence will achieve remarkable results in the coming years.

(Source: Hexi University)

Note: This article is copyrighted by the original author and source. If there are any copyright issues, please contact us promptly, and we will correct or delete the relevant content immediately.

Leave a Comment Cancel reply