Information recommendation method and device, electronic equipment and storage medium

Abstract

The invention relates to an information recommendation method and apparatus, an electronic device and a storage medium. The method comprises the steps of determining a first identifier and a pluralityof candidate second identifiers; inputting the first identifier into a trained neural network model, and obtaining a first identifier vector of a specified dimension corresponding to the first identifier and output by an intermediate layer of the neural network model; respectively inputting the second identifiers into the neural network model, and obtaining a second identifier vector which is output by a middle layer of the neural network model and corresponds to the second identifiers and has a specified dimension; and matching the first identifier vector with each second identifier vector,and determining a second identifier to be recommended to the first identifier from the plurality of second identifiers according to a matching result. The information recommendation is realized in a high-dimensional space, so that a plurality of limiting conditions for directly constructing explicit user identifiers for matching can be avoided, and the recommendation efficiency and accuracy are improved.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, and in particular to an information recommendation method, device, electronic equipment, and storage medium. Background technique [0002] With the development of Internet advertising technology and business, crowd targeting is almost one of the basic functions of every advertising platform. User interest tags are the basis for precise crowd targeting. [0003] In related technologies, user interest tags are determined by establishing an interest tag model based on user behavior data. The model extracts video tags by segmenting video titles and descriptions, maintains a user interest tag system, and establishes a mapping between video tags and user interest tags. relation. [0004] However, in related technologies, user interest tags are explicit interest tags, and there are many restrictions, such as difficulty in recalling similar content based on explicit tags. Contents of...

Images