Research Of The Pattern Knowledge Supported Personalized Learning Path Recommendation Method

As a new form of teaching,online teaching has gradually become a new economic growth point and a research focus in the field of education because it has realized the space and time expansion of traditional teaching and the sharing of resources.However,most of the current online teaching only improves the traditional teaching technically.Compared with the traditional teaching,the online teaching does not have an essential breakthrough,and it is essentially the networked extension of the traditional teaching.According to the constructivism learning theory,tacit knowledge is the core and essence of human learning,which determines people's learning ability.The real goal of teaching is to teach tacit knowledge.Therefore,how to support the teaching of tacit knowledge and realize the cultivation of learning ability is the key and core of the development of online teaching.This article aims at the key problem in the online teaching--the learning path recommendation,and takes the constructivism learning theory as an instruction to research a learning path recommendation method that supports pattern knowledge.Firstly,based on the constructivist learning theory,combined with the new knowledge expression model,the learning characteristics model that supports pattern knowledge is proposed from the two dimensions of learning behavior characteristics and learning state characteristics.Secondly,combined with the above learning characteristics model,a personalized learning path recommendation algorithm that supports pattern knowledge is proposed.Ant colony algorithm is widely used in the field of path planning due to its advantages of self-organization,distributed multi-agent and positive feedback.Therefore,the algorithm for learning path recommendation proposed in this paper is based on the ant colony algorithm.Finally,the learning path recommendation algorithm is implemented on the online teaching prototype system,and an experiment is carried out to verify the feasibility,adaptability and effectiveness of the algorithm.