Recommendation system with metric transformation
US9454580B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 8, 2016 |
| Grant date | Sep 27, 2016 |
| Priority date | — |
| Expiry date | Feb 8, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F16/9535
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Example apparatus and methods transform a non-metric latent space produced by a matrix factorization process to a higher dimension metric space by applying an order preserving transformation to the latent space. The transformation preserves the order of the results of an inner product operation defined for the latent space. The higher dimension metric space may be queried for the results to different requests. Example apparatus and methods may assign every user i a vector ui in a latent space, and may assign every item j a vector vj in the latent space. The dot product ui·vj represents the score between the user i and the item j. The score represents the strength of the relationship between the user i and the item j. Example apparatus and methods may then apply ranking methodologies (e.g., LSH, K-D trees) to problems including recommendation, targeting, matchmaking, or item to item.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.