Recently, with the rapid development of information technology, emerging technologies represented by artificial intelligence are widly applied in education, triggering profound changes in the concept and mode of learning. And, online learning transcends the limitations of time and space, providing more possibilities for learners to learn “anytime and anywhere”. However, the separation of time and space of teachers and students in online learning makes teachers could not handle students’ learning process, limits the quality of teaching and learning. Diversified learning targets and massive learning resources generate some new problems, i.e., how to quickly accomplish learning targets, reduce learning costs and reasonably allocate learning resources. And these problems have become the limitations of the development of individuals and the society. However, traditional “one -size -fits-all” educational model can no longer fit human’s nedds, thus, we need one more effieient and scientific personalized education model to help learners maximize their learning targets with minimal learning costs. Based on these considerations, what we need is to new adaptive learning system which could automatically and efficiently identify learner personalized characteristics, efficiently organize and allocate learning resources, and plan a global personalized learning path. In this paper, we systematically review and analyze the current researches on personalized learning path recommendation, and we analyze different research sight from multidisciplinary perspective. Then, we summarize the most applied algorithm in current research. Finally, we highlight the main shortcomings of the current rearch, which we should pay more attention to.