Sequence recommendation method based on multi-modal feature fusion

By extracting and fusing image, text and ID features, and using Transformer and DNN layers for multimodal feature fusion, combined with attention masking mechanism, the problem of poor multimodal feature fusion in the prior art is solved, and the accuracy and stability of recommendations are improved.

CN119783044AInactive Publication Date: 2025-04-08NORTHEASTERN UNIV CHINA
2 Cites 9 Cited by

Patent Information

Application Number
CN202510272048.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-10
Publication Date
2025-04-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing sequence recommendation method has shortcomings in feature representation learning, especially when multimodal features are fusion, it is difficult to effectively learn information in multimodal features, resulting in insufficient recommendation accuracy and stability, especially in the face of new projects.

Method used

A sequence recommendation method based on multimodal feature fusion is adopted to extract image, text and ID features, and multimodal feature fusion and learning using Transformer layer and DNN layer, combined with attention masking mechanism, ensure that each modal feature can fully utilize its own advantages during the interaction process.

Benefits of technology

It effectively retains rich information in text and image features, improves the model's understanding and learning ability of the project, and enhances the accuracy and stability of recommendations, especially when facing new projects and cold-start scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a sequence recommendation method based on multi-modal feature fusion, and relates to the technical field of personalized recommendation. The method comprises the following steps: firstly, extracting multi-modal features according to different modal interaction records of a user; different feature extraction methods are adopted for different modes; then carrying out multi-modal feature fusion and learning by adopting a multi-modal fusion module; constructing a multi-modal fusion sequence recommendation model to perform sequence recommendation; according to the method, by means of an attention mask mechanism, each mode can pay attention to information in the own mode, information interaction between the modes can also be achieved, and rich original information in text and image features is effectively reserved. According to the method, the problem that a traditional multi-modal recommendation model is disordered during feature fusion is solved. Meanwhile, the situation that in the prior art, it is difficult to balance ID feature learning and multi-modal feature learning is improved, and the recommendation ability of the model in the face of long-tail projects and cold start scenes is enhanced.
Need to check novelty before this filing date? Find Prior Art