EK-Chess: Chess Learning System Based on Top-Level Chess Expert Knowledge Graph

Abstract

Chess, as a form of intellectual sport, has garnered significant attention from researchers, driving continuous research into computer-assisted player training. However, contemporary teaching or training models frequently confine learners to passive observation of computer-generated results. Beginners may find it challenging to comprehend the cognitive processes underlying decision-making. To address this issue, this article proposes EK-Chess, a knowledge graph-based chess teaching system that encompasses a series of endgame teaching scenarios. This system assists chess beginners in learning the positional evolution in pawn endgames, helping users comprehend offensive and defensive strategies in endgames. User studies validate the effectiveness, and support of the system in endgame learning.

Keywords:

• Learning system
• chess beginner
• chess education
• expert knowledge
• knowledge graph
• user study

Acknowledgments

We would like to thank our participants for generously contributing their time and valuable insight. We also appreciate the constructive feedback and suggestions provided by top-level chess experts and chess teachers, which helped improve this work.

Disclosure statement

There is no conflict of interest among the authors.

Additional information

Funding

This work is supported by the [Natural Science Foundation of Beijing & Key project of Science and Technology Plan of Beijing Municipal Education Commission] under Grant [No. 21JD0044]; [National Natural Science Foundation of China] under Grant [No. 61872363]; the Beijing Natural Science Foundation under Grant No. L232098; and the Strategic Priority Research Program of Chinese Academy of Sciences under Grant No. XDA27000000.

Notes on contributors

Mingyu Zhang

Mingyu Zhang is a master student in artificial intelligence at University of Chinese Academy of Science, China. His research interests include human–computer interaction, natural language processing and machine learning.

Qiao Jin

Qiao Jin is a PhD candidate from Grouplens Research Center at the University of Minnesota – Twin Cities. Her research focuses on using AR/VR/MR to support remote education, collaboration, and social connection.

Qian Dong

Dong Qian is a lecturer at School of Physical Education, Shanghai University of Sport. She received her Ph.D. degree in Peking University. She is national first-class athletes in chess. Her research interest includes educational technology, instructional design in Physical education, and chess education.

Danli Wang

Danli Wang is a professor at the Institute of Automation, Chinese Academy of Sciences, Beijing, China. She received her Ph.D. degree in Beihang University. Her research interests include human–computer interaction, user experience, artificial intelligence, physiological computation, and group recommendation.

Jun Xie

Jun Xie serving as vice president of Capital University of Physical Education and Sports currently. She received her Ph.D. degree in Beijing Normal University. She has won four times world champion of women’s chess. Her research interests include cognitive psychology, Olympic movement, leisure sports, and intelligence movement.