Dialogue recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a dialogue recommendation method and device, electronic equipment and a medium, and the method employs a historical sequence to improve the recommendation efficiency, and comprises the steps of: obtaining a historical interaction sequence between a user and an item, inputting the historical interaction sequence into a recommendation network model comprising an embedded layer, a self-attention block and a prediction layer, and carrying out the training, and generating an item preference value, wherein the item comprises item attributes; generating a candidate item set by using the item preference value and items without interaction with the user; when a preference item attribute sent by a user is received, updating the candidate item set by using the preference item attribute, and calculating an interaction prediction value of each candidate item in the updated candidate item set by using the item correlation value; generating a candidate attribute set by using the interaction prediction value and the candidate items, and calculating a preference prediction value of each candidate item attribute in the candidate attribute set by using the interaction prediction value; and inputting the calculated candidate item set and candidate attribute set into a strategy network for reinforcement learning, and carrying out dialogue recommendation to the user.

Description

technical field [0001] The present invention relates to the field of dialogue recommendation, in particular to a dialogue recommendation method, device, electronic equipment and storage medium. Background technique [0002] Conversational Recommender System (CRS, Conversational Recommender System) is a recommendation system that can actively obtain preference attributes from users and use this attribute to recommend items. In related technologies, dialogue recommendation can use the preference attributes currently asked by the user for recommendation, and it can consider the historical items that the user has interacted with to ask the user for preference attributes or recommended items, but ignores the interaction between the user and the historical items The influence of order on recommendation but ignores the importance of the sequence of interaction history items, which makes it difficult for existing dialogue recommendation methods to efficiently and accurately perform ...

AI Technical Summary

Problems solved by technology

In related technologies, dialogue recommendation can use the preference attributes currently asked by the user to make recommendations, and it can consider the historical items that the user has interacted with to ask the user for preference attributes or recommended items, but ignores the interaction between users and historical items The impact of order on recommendation but ignores the importance of the sequence of interaction history items, which makes it difficult for existing dialogue recommendation methods to efficiently and accurately perform dialogue recommendations with users

Images