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

user-5d4bc4a8530c70a9b361c870(2019)

引用 1|浏览2
暂无评分
摘要
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.
更多
查看译文
关键词
Recommender system,Coding (social sciences),Data mining,Computer science,Evaluation result
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要