Personalized recommendation method based on commodity property entropy
A product attribute and recommendation method technology, applied in marketing and other directions, can solve problems such as low efficiency of content recommendation, achieve the effect of maintaining the recommendation hit rate, effective recommendation, and improving diversity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0034] The present invention proposes a new way of analyzing user profile, figure 2 This is an example of the user profile of the present invention. The figure shows a user profile with five attribute classifications and the statistics of brand attribute labels. The statistics of each attribute classification will finally be transformed into the entropy value of the corresponding classification. It is a user in a broad sense, so the global entropy value can also be obtained using this method. According to the user's entropy value in different classifications, combined with the entropy value of the overall classification, the user classification entropy value is converted into weight. Use weights to calculate the similarity between the products in the recommended candidate set and the products seen by the current user to complete the rearrangement of the original recommendation sequence. This method tends to recommend relatively unpopular products to users, thereby providing use...
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.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap