一种科技成果转化的智能推荐方法及系统
By establishing a recommendation model based on user behavior and content characteristics, and combining it with synergistic resonance weighted fusion, the shortcomings of the technology transfer platform in terms of recommendation have been addressed, enabling personalized and novel technology transfer recommendations, thereby improving user experience and transfer efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV OF TECH SCI & TECH PARK CO LTD
- Filing Date
- 2024-05-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technology transfer platforms lack recommendation functionality. Item-based collaborative filtering algorithms suffer from cold start problems, and content-based recommendation algorithms lack novelty and are unable to recommend new types of technological achievements to users.
By collecting user and scientific and technological achievements data, a recommendation model based on user behavior and content features is established. A collaborative resonance weighted fusion model is used for prediction and recommendation. Reasonable preference values and time factors are set, the similarity of scientific and technological achievements is calculated, keyword features are extracted using TF-IDF, and weighted fusion recommendation is performed by comprehensively considering vector differences and time effects.
It improves the personalization and novelty of technology achievement recommendations, enhances the effectiveness of recommendation algorithms, and improves the user experience on the platform and the efficiency of technology achievement transformation.
Smart Images
Figure CN118503535B_ABST