A hybrid recommendation method based on sparse edge denoising and automatic coding

Abstract

The invention relates to a hybrid recommendation method based on sparse edge noise reduction automatic coding, belonging to the personalized recommendation field. The invention comprises the followingsteps: firstly, merging each commodity comment into a comment document; using TF-IDF processes the review text for each product and selects the word with the highest TF-IDF value to construct the commodity content vector as the feature representation of the commodity. Secondly, the sparse edge denoising automatic coding model is trained with commodity content vector, the commodity features are extracted from the commodity content vector with the trained model, and the similarity of the commodity feature vector is calculated with cosine similarity, so as to obtain the influence of the nearestneighbor commodity. Finally a predication score is obtained through combination of neighbor commodity influence and user-evaluation matrix deposition. The invention effectively improves the algorithmefficiency and the recommendation accuracy.

Description

technical field [0001] The invention relates to a hybrid recommendation method based on sparse edge noise reduction automatic coding, which belongs to the field of personalized recommendation. Background technique [0002] With the advent of the era of big data, major Internet companies are paying more and more attention to data, especially the actual needs of major domestic and foreign e-commerce websites are the driving force for promoting the research of recommendation algorithms. On e-commerce websites and social networks at home and abroad, the most common recommendation algorithm is to recommend products or topics that users may buy or are interested in based on the user's historical behavior data. In a real recommendation system, there are two main factors affecting the recommendation accuracy: data sparsity and cold start. Data sparsity means that on the actual e-commerce website, silent users account for the majority, and only a small number of users comment. The n...

AI Technical Summary

Problems solved by technology

In order to make comprehensive use of review text and review information to improve the effectiveness of the recommendation system, Hao Wang (35th Hawaii International Conference on System Sciences>, 2012) et al. proposed a deep collaborative model CDL, which solves the problem of learning hidden features of the CTR model when the data is sparse. Inadequate bug, which doesn't account for silent users

At present, domestic researchers, Zhang Min (, 2015, 30(3)) proposed the hidden factor model (SELFM) to strengthen the semantics, using the deep model SDAE to extract the text features of product reviews, and User reviews are combined with ratings to improve the accuracy of rating predictions, but SDAE's learning ability and classification accuracy are not as good as SmDAE

Images