A sequential social recommendation method, system and storage medium based on gate mechanism

Abstract

The invention relates to a sequence social recommendation method, system and storage medium based on a gate mechanism. The method includes: dividing the original consumption data of users and friends into sequences, and initializing to obtain user sequence data and friend sequence data; GRU neural network based on a selection gate mechanism Get the current interests of users and friends; network splicing based on the selection gate mechanism to get the short-term interests of friends, initialize the product data of friends to get the long-term interests of friends, and splice the short-term interests of friends and long-term interests of friends to get the final interests of friends ; The neural network based on graph attention gets the influence of friends, splicing the influence of friends and the current interest of the user to obtain the final interest of the user; calculates the probability distribution of different commodities, performs model training according to the probability distribution, and reports to the user according to the training model Recommend product information; through the selection gate mechanism, the user's interest can be learned more accurately, so that the recommendation performance of the recommendation system can be further improved.

Description

technical field [0001] The present invention relates to the technical field of recommendation systems, in particular to a method, system and storage medium for sequential social recommendation based on a gate mechanism. Background technique [0002] The recommendation system analyzes the user's behavior and finds the user's personalized needs, so as to recommend some products to the corresponding users, helping users find the products they want but are difficult to find. There are various existing recommender system models, such as RNN-based sequential recommender systems: given a series of historical user-item interactions, RNN-based sequential recommender systems attempt to predict the next One possible interaction, in addition to basic RNNs, long short-term memory (LSTM) and gated recurrent unit (GRU)-based RNNs have also been developed to capture long-term dependencies in sequences; another example is the combination of base-remainder sequences with social This recommen...

AI Technical Summary

Problems solved by technology

There are various existing recommender system models, such as RNN-based sequential recommender systems: given a series of historical user-item interactions, RNN-based sequential recommender systems try to predict the following by modeling the sequential dependencies of the given interactions A possible interaction, in addition to the basic RNN, long short-term memory (LSTM) and gated recurrent unit (GRU)-based RNN has also been developed to capture long-term dependencies in sequences; another example is the combination of residual sequences and social Recommendation system, this recommendation system not only utilizes the user's own interests but also combines the influence of friends to improve the performance of the recommendation system, but the existing technology is not accurate in learning the user's interest in the process of learning the user's interest to express the user's real interest

Images