In recent years explosive increase and variety of information due to the progress of the internet. Therefore, decision making in different fields has faced different challenges. Recommender systems provide personalized services to users by identifying users' interests, filtering information, and managing information, especially contextual information. Similarity criteria based on contextual information is a way to reduce the challenge of starting a cold. We argue that similarity is a vague concept, and we more realistic results in recommender systems using fuzzy logic. Applying fuzzy logic to contextual information can be an effective way to identify ambiguities and uncertainties in measuring the similarity of items and users. In this paper, we present a new multilevel contextual fuzzy similarity criterion with SVD matrix for recommending systems called FCSVD Which is based on a combination of similarity criteria PSS, fuzzy rules and contextual information. The results show an improvement in the accuracy of the method recommendations FVSVD compared to the CACF, CTLSVD, MF-LOD and CFSVD methods according to evaluation measure Precision, Recall, F1-score.