User personalized preference prediction method based on multi-angle non-transfer preference relationship
A technology of preference relationship and prediction method, applied in data processing applications, special data processing applications, instruments, etc., can solve the problems of no longer satisfying transitive characteristics, complex factors, etc., to eliminate uncontrollable subjective accidental errors, preference prediction Accurate and Guaranteed Scientific Results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example
[0091] The user preference scoring process will be used for new users, that is, the scoring object is unknown to the user. The selected target samples should have similarity and specificity, that is, belong to the same kind of items or content, but have obvious differences in appearance or function.
[0092] Such as figure 2 As shown, the designer combines the many factors that affect the user's choice, firstly defines the user preference matrix relationship, in order to evaluate the specific characteristics and attributes of the object, and confirm different inspection angles and different inspection dimensions of the corresponding angles. The user independently scores the target object according to the attributes specified in the preference matrix. The more they like a certain attribute, the higher the corresponding score and weight. The result of matrix calculation reflects the user's strong preference for the target clothing.
[0093] Take "clothing preference" as an example ...
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