Knowledge graph and time sequence feature fused interpretable interest point recommendation method
The invention discloses an interpretable point-of-interest recommendation method fusing knowledge graph and time sequence features, and relates to the technical field of point-of-interest recommendation. The method mainly comprises three parts: knowledge graph construction, potential relationship re...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
16.11.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses an interpretable point-of-interest recommendation method fusing knowledge graph and time sequence features, and relates to the technical field of point-of-interest recommendation. The method mainly comprises three parts: knowledge graph construction, potential relationship representation learning among entities, time sequence dynamic capture of user behaviors and explainable recommendation result output, the potential relationship representation learning among the entities is realized based on the constructed knowledge graph, and by capturing a plurality of potential relationship paths among the entities, potential relation representation among entities is learned, user preferences are learned by utilizing a sign-in sequence of a user, namely path static information and time sequence dynamic information are fused, finally interest points are recommended for the user based on the learned user preferences, and explanation of a recommendation result is provided. According to the method, t |
---|---|
Bibliography: | Application Number: CN202110972282 |