Self-attention network information processing method for streaming media recommendation

Abstract

The invention discloses a self-attention network information processing method for streaming media recommendation. The method comprises the following steps: injecting a position embedding matrix intoan input embedding matrix to obtain a final input embedding matrix; normalizing the final input embedded matrix to obtain a linear projection onto the three matrixes to obtain Q, K and V, and obtaining a weight to obtain an output H1 representing interaction between items in the session in the first self-attention; performing self-attention splicing on the outputs representing the interaction between the items in the session to obtain an interaction S representing the final item in the session; summing the E and the S, performing layer normalization processing to obtain a matrix F representinguser preferences through feedforward network processing, and obtaining each layer of matrix representing the user preferences by applying a nonlinear activation function on the basis of multi-head self-attention; and calculating the score ri of the candidate item vi belonging to V, and determining the probability that the user clicks the candidate item vi according to ri.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a self-attention network information processing method for streaming media recommendation. Background technique [0002] Given the large amount of information in people's lives, how to obtain effective information from a wide range of data has become an urgent problem. The recommendation system can provide personalized recommendations for different users, so that each user can obtain the information they want from the limited and diverse information screened by the recommendation system, especially in streaming media scenarios. [0003] Traditional recommender systems usually utilize informative user logs to model user preferences and recommend items that users may be interested in. In other words, each user must have sufficient interaction records, and the user identity must be visible in each interaction event. However, in many online systems, such as e-commerce sit...

AI Technical Summary

Problems solved by technology

Although the above methods can achieve relatively advanced results to a certain extent, they have some limitations, such as the inherent sequential nature of RNN-based methods does not support parallelism, or previous work can reveal the importance of item inte

Images