Information cross-domain parallel sequence recommendation method based on shared account, medium and equipment

user-5d4bc4a8530c70a9b361c870(2019)

Cited 1|Views6
No score
Abstract
The invention provides an information cross-domain parallel sequence recommendation method based on shared account, a medium and equipment. The method comprises the steps: extracting watching sequences of a given account in different fields, and carrying out the coding of the watching sequences, and obtaining the mixed representation of the given account in a single field; identifying different user behaviors by learning the hybrid representation, and filtering out information which may be useful for another domain; migrating the useful information of each field to other corresponding fields;and integrating useful information filtered in different fields, evaluating each piece of related information, and recommending the related information to the corresponding account according to an evaluation result. The problems of cold start and data sparsity frequently appearing in a recommendation system are solved.
More
Translated text
Key words
Recommender system,Coding (social sciences),Data mining,Computer science,Evaluation result
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined