Research On The Standardization Method Of Course Knowledge In Big Data Environment

With the extensive and in-depth application of cloud classroom,the network course,mobile learning and other teaching forms in the field of education,as well as the continuous construction of 2.0 action of educational informationization,the number of course materials is growing,the content of teaching materials is constantly enriched,and a large number of curriculum materials resources have been accumulated.These teaching materials have sophisticated contents and mixed quality,which results in the problem that the knowledge's description is incomplete and the content description is inconsistent in the course teaching materials.These irregularities cause learners to deviate from their understanding of knowledge,and also make some knowledge-based services do not achieve the desired results.In this paper,the method of knowledge representation is studied.The basic form which representation of knowledge is studied,understands non-standard knowledge from cognitive logic according to the Theory of knowledge representation,and concludes that knowledge is composed of attribute and attribute value.The irregularities of curriculum knowledge are also mainly related to attributes and attribute values.The model of the knowledge point representation is proposed,the method of acquiring knowledge attributes is given.In the knowledge point model is given,and on the basis of the model of knowledge representation,the problem of irregularities is pointed out and the normalization strategy is given.This paper studies the processing method of inconsistent knowledge,puts forward the method of inconsistent processing of atomic knowledge based on co-meaning digestion,firstly,making use of the distance between words with the word type,part of speech and meaning characteristic measurement,and then uses the hierarchical clustering algorithm and the K-Means algorithm to deal with the two schemes,Finally,the number of optimal co-finger chains is determined based on contour coefficients to solve the problem of inconsistency of atomic knowledge words.This thesis studies the processing method of incomplete knowledge,and put forward a method of attribute value inconsistency processing based on digest technology.This paper introduces detailed the specific process of describing the importance calculation,screening and ridding unbalance of sentence,and generates standardizing sentence.Firstly,the improved sentence importance calculation method based on the word cluster is used to rate the sentence describing the knowledge attribute of the course,and then the sentence is filtered and streamlines sentences by using the maximum interval algorithm,and the complete structured information is finally generated.This method is applied to solve the problem of incomplete attribute and incomplete expression of original knowledge,and to transform incomplete knowledge into complete knowledge.