Patent · US Active

Systems and methods of selecting content items using latent vectors

US9110955B1 · kind B1 · utility

62Cited by
1References
16Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJun 5, 2013
Grant dateAug 18, 2015
Priority date
Expiry dateNov 26, 2033

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F16/24578
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A two-dimensional matrix of data points represents occurrences of users selecting content items, such as audio tracks. A server computes n-dimensional latent vectors for each user and for each item. The server iteratively optimizes the user vectors and item vectors based on the data points. Each iteration includes a first phase in which the item vectors are held constant, and a second phase in which the user vectors are held constant. In the first phase, the server computes first phase parameters based on data points, the user vectors, and the item vectors, and updates the user vectors. In the second phase, the server similarly computes second phase parameters for the item vectors and updates the item vectors. The server receives a request from a user for an item recommendation, and selects an item vector based on proximity in n-dimensional space. The server then recommends the selected item to the user.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.