Abstract: In recent years,code similarity detection has been a hot topic in the field of software engineering,which can help code clone detection,code defect prediction,and reduce the cost of software maintenance.At present,most popular code similarity detection methods build language processing model to extract the text,syntax,structure and other feature information of source code from tokens,AST and other code representations,and map them to real value vectors in continuous space.Then,obtain the similar value of the code comparison by calculating the Euclidean distance and cosine value of the extracted features or by the shallow neural network model.These methods have achieved better results than the traditional static analysis program.However,most of these methods are based on the grammar level of source code,which can not make full use of the semantic information of source code.Although Doc2Vec and Word2Vec can extract the lexical semantic information of code,they are powerless to handle the execution semantic information of code.To solve this problem,control flow graph(CFG) is proposed to represent the execution semantics of code,and the graph embedding method based on random walk is used to learn and reason the semantic information of the code,and then judge the functional similarity of the source code.Compared with Doc2Vec and Word2Vec methods,experimental results show that the model can accurately detect the functional similarity of source code,and its F1 value improves by 16.01% and 18.72% compared with Doc2Vec and Word2Vec methods,respectively.

Key words: Control flow graph, Graph embedding, Random walk, Code similarity detection