A Knowledge Graph, also known as knowledge domain visualization or knowledge domain mapping, is a series of different graphics that display the development process and structural relationships of knowledge. It describes knowledge resources and their carriers using visualization technology, mining, analyzing, constructing, drawing, and displaying knowledge and their interconnections. The Knowledge Graph achieves the goal of interdisciplinary integration by integrating the theories and methods of disciplines such as artificial intelligence, applied mathematics, graphics, and information visualization, and visually presenting the core structure, development history, cutting-edge fields, and overall knowledge architecture of the disciplines.

The construction of Knowledge Graphs lays the foundation for the current evolution of artificial intelligence from perceptual intelligence to cognitive intelligence. With the development of technology, artificial intelligence has reached or surpassed human levels in perceptual intelligence fields such as “listening, speaking, and seeing,” but it is still in the early stages in cognitive intelligence fields that require external knowledge, logical reasoning, or domain transfer. Cognitive intelligence will draw inspiration from cognitive psychology, brain science, and human social history, using technologies such as Knowledge Graphs, causal reasoning, and continuous learning to establish effective mechanisms for stable acquisition and expression of knowledge, allowing knowledge to be understood and utilized by machines, thus achieving a critical breakthrough from perceptual intelligence to cognitive intelligence.

A Course Knowledge Graph is the structured and visualized result of course content formed by using subject experts and AI technology to manually or automatically sort course content, extract course knowledge points, and establish a network structure of relationships between knowledge points and course resources.

The Knowledge Graph serves as a refinement and summarization of course content, with extensive applications. Especially in online education, the combination of Knowledge Graphs and AI recommendation algorithms can provide personalized education for each student based on their mastery of knowledge points, plan learning paths, and display learning conditions, thus achieving tailored teaching for every individual. Typical application scenarios include:

– Course Knowledge Point Graph Display

– Intelligent Adaptive Learning: Learning Path Display, Learning Resource Recommendation, Learning Condition Reports

– Learning Assistant Robots (Automated Course Q&A)

– Intelligent Lesson Preparation

The Course Knowledge Graph is a product of the combination of AI technology and education, and the various applications based on it are the main battleground of AI + education, particularly AI + online education. The vast online educational resources and intelligent adaptive learning based on Knowledge Graphs represent a significant disruption to the traditional education model of “one teacher for many students” that has lasted for thousands of years.

Aopeng Education, as a leading enterprise in online education, has thousands of course resources covering dozens of subjects and hundreds of majors. It has an urgent demand for the construction of Course Knowledge Graphs and possesses unique data advantages such as courseware and corpus resources required for the construction of Course Knowledge Graphs.

Since 2019, the engineering center has collaborated with the product center, student user division, and industry-education integration to conduct various attempts at the construction and application of Course Knowledge Graphs. This has been done in stages and batches to increase the knowledge graph construction and related applications for courses/majors.

Through continuous exploration, experimentation, and pre-research by the AI innovation group of the engineering center on relevant technologies and algorithms, a semi-automated and semi-manual (90/10) method has been gradually developed to extract course knowledge points, identify the overall relationships between knowledge points, and associate knowledge points with resources (videos, documents, exam questions).

The methods mainly include: video content analysis (OCR), audio content analysis (speech recognition ASR), syllabus analysis (web scraping, data cleaning), knowledge point extraction (natural language processing), overall relationship identification between knowledge points (natural language processing), and association of knowledge points and resources.

Depending on the different styles of each course and resource types, the AI technology automatically extracts and identifies knowledge points, combined with manual correction, forming a production line that allows the construction of a course’s Knowledge Graph to be completed within 1-2 person-days. Feedback from teachers in the product center indicated that manually constructing a course Knowledge Graph used to take half a month to a month. It is evident that the AI technology’s automated extraction production line method significantly improves the efficiency of constructing Course Knowledge Graphs.

Course Knowledge Graph Construction Production Line

By comparing the knowledge points extracted by teachers manually and those extracted automatically by AI for the same course (“Introduction to the Basic Principles of Marxism”), it can be observed that the AI-extracted knowledge points have a finer granularity, with the number of extracted knowledge points being four times that of manually extracted points.

Comparison of Knowledge Points Extracted Manually (Left) and by AI (Right) for the Same Video Segment

Hierarchical Structure of Knowledge Points Extracted by AI from the Above Video Segment

AI-Generated Knowledge Graph for the Fujian Normal University Version of “Introduction to the Basic Principles of Marxism”

The total duration of the course is 14 hours and 29 minutes, with a total of 466 knowledge points extracted by AI.

AI-Generated Knowledge Graph for the Fujian Normal University Version of “Introduction to the Basic Principles of Marxism”

Note: In the above image, the orange nodes represent a specific knowledge point, the green nodes represent associated exam questions, and the yellow nodes represent associated videos. The “Teach” relationship attribute between videos and knowledge points contains information such as the knowledge point’s startTime and endTime, which can be used for precise video recommendations.

As of now, Aopeng has 30 course Knowledge Graphs generated manually by teachers in the product center and 4 course Knowledge Graphs generated by the latest AI technology. Various application scenarios have been developed based on these.

* Course Learning Condition Reports

* Exam Question Recommendations Based on Mistakes (Error Book)

* Precise Video Recommendations Based on Mistakes

* Automated Q&A Based on FAQs (in development)

In the future, while continuing to promote the construction of more Course Knowledge Graphs, various application scenarios will be developed based on the content of existing Knowledge Graphs.

The construction and application of Course Knowledge Graphs is an ongoing process. On one hand, the accuracy of AI algorithms and the level of automation in the production line can be further improved; on the other hand, the automatic discovery of more relationships between knowledge points (e.g., prerequisite relationship identification) will lay a solid disciplinary knowledge foundation for applications such as intelligent adaptive learning planning. The introduction of external knowledge (e.g., Baidu Encyclopedia, Chinese Wikipedia) will greatly improve the algorithm accuracy for the construction and application of Knowledge Graphs. The AI group will focus on continuously improving the construction and application capabilities of Knowledge Graphs in the following aspects:

* Introduction of External Encyclopedia Knowledge (Baidu Encyclopedia, Chinese Wikipedia)

* More Relationship Identification Between Knowledge Points (Prerequisite Relationships, Equivalence Relationships, etc.)

* Generation of Subject Knowledge Graphs (Cross-Course Subject Terminology Graphs)

* OCR Automatic Recognition Technology for Scientific Formulas

* Automatic Error Correction for Speech Recognition Results

* Online Book Knowledge Graph Construction Platform

* Automated Q&A Based on Knowledge Graphs

* Applications of Various Reasoning and Recommendation Algorithms Based on Graph Machine Learning

* Collaborative Filtering Recommendation Systems (Based on XAPI User Behavior Collection)

* Intelligent Lesson Preparation

* Adaptive Learning Systems

The development and application of artificial intelligence technology is the most important and core technological trend of the 21st century. With the continuous introduction and maturation of relevant algorithms, artificial intelligence has been widely applied in areas such as facial recognition, intelligent recommendations, and intelligent customer service.

AI + online education based on Knowledge Graphs will lead to profound changes in educational models and learning methods. The AI innovation team of the engineering center will deeply explore this blue ocean field of AI + education, continuously innovate by combining business innovation with technological innovation, and use innovation to build a unique technological moat for Aopeng online education.