Invention Grant
- Patent Title: Scalable matrix factorization in a database
-
Application No.: US16843334Application Date: 2020-04-08
-
Publication No.: US11948159B2Publication Date: 2024-04-02
- Inventor: Amir H. Hormati , Lisa Yin , Umar Ali Syed , Mingge Deng
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Honigman LLP
- Agent Brett A. Krueger
- Main IPC: G06F16/332
- IPC: G06F16/332 ; G06F16/22 ; G06F16/2453 ; G06F17/16 ; G06F18/214 ; G06N5/04 ; G06Q30/0201

Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable matrix factorization. A method includes obtaining a Structured Query Language (SQL) query to create a matrix factorization model based on a set of training data, generating SQL sub-queries that don't include non-scalable functions, obtaining the set of training data, and generating a matrix factorization model based on the set of training data and the SQL sub-queries that don't include non-scalable functions.
Public/Granted literature
- US20200320072A1 SCALABLE MATRIX FACTORIZATION IN A DATABASE Public/Granted day:2020-10-08
Information query