News recommendation method based on comparative learning
A recommendation method and news technology, which is applied in the field of news recommendation based on comparative learning, can solve the problem of inaccurate recommendation of the news recommendation system, and achieve the effects of improving coding ability, robustness, and strong modeling ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.
[0019] For news about the same event, different authors will have different descriptions. like figure 1 As shown, the two news stories are both describing the "Chinese women's curling victory over the UK", but there are differences in the text and entities of the two. Here the text is the title of the news, and the entity is the entity word extracted from the news title. Entity extraction can be done in two ways: simple text matching and named entity recognition based on deep learning. We can see that the content of the events conveyed by two news with different text descriptions is essentially the same. Therefore, the model should make the encoded vector representations of two news close to each other when encoding the text, while keeping dissimilar news far away from each other. figure 2 is an example of user interest extraction, user 1 br...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com