Construction method of interpretable recommendation model based on knowledge graph

The invention discloses a construction method of an interpretable recommendation model based on a knowledge graph, which comprises the following steps: S1, converting entity and relationship category data in the knowledge graph into embedded vectors through Word2Vec, and splicing the embedded vector...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: PENG JIAN, YI PEIYU, HUANG FEIHU, XU BING
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a construction method of an interpretable recommendation model based on a knowledge graph, which comprises the following steps: S1, converting entity and relationship category data in the knowledge graph into embedded vectors through Word2Vec, and splicing the embedded vectors to form a sentence matrix; s2, processing the sentence matrix through a convolution kernel to obtain different feature mappings; s3, enabling different feature mappings to pass through a pooling layer, and enabling different path sequences to be pooled and then subjected to fixed-length feature representation; s4, inputting the features output by the pooling layer into the RNN network, and outputting an implicit vector as a path representation; s5, predicting the interaction probability of the user and the candidate item based on a weighted pooling function, calculating score contributions of different paths, and selecting the path with the maximum score as recommendation; s6, evaluating the recommended path by a