Collaborative filtering method based on coupling topic model
A topic model and topic technology, applied in the field of information recommendation of Internet products, can solve problems such as poor interpretability of feature vectors, and achieve the effect of solving sparse problems
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0018] The present invention proposes a coupled topic model based on matrix decomposition and topic model. By mapping users and products to the hidden topic space, learn a K-dimensional feature vector η for each user and product, and replace Dirichlet prior by introducing logistic normal prior, so that the topic vector θ( While K is the number of topic vectors), a more flexible feature vector η can be learned, which is no longer limited to the corresponding simplex (a K-dimensional vector θ satisfies Then it is said that the vector is distributed on the simplicity of K-1), which not only makes the eigenvector more expressive, but also makes it more flexible to use matrix decomposition for scoring prediction.
[0019] ...
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