公开(公告)号：US20220382564A1

公开(公告)日：2022-12-01

申请号：US17819134

申请日：2022-08-11

Applicant: Twitter, Inc.

Inventor： Sean Moon ,  Arvind Thiagarajan ,  Mike Jahr ,  Milind Ganjoo ,  Parag Agrawal

IPC: G06F9/445 ,  G06F16/903 ,  H04L9/40 ,  G06F21/55 ,  G06F16/9032 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

公开(公告)号：US10649794B2

公开(公告)日：2020-05-12

申请号：US15675671

申请日：2017-08-11

Applicant: Twitter, Inc.

Inventor： Sean Moon ,  Arvind Thiagarajan ,  Mike Jahr ,  Milind Ganjoo ,  Parag Agrawal

IPC: G06F16/00 ,  G06F9/445 ,  G06F16/903 ,  H04L29/06 ,  G06F21/55 ,  G06F16/9032 ,  G06N20/00 ,  G06N3/08 ,  G06Q50/00

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

公开(公告)号：US11416268B2

公开(公告)日：2022-08-16

申请号：US15929375

申请日：2020-04-29

Applicant: Twitter, Inc.

Inventor： Sean Moon ,  Arvind Thiagarajan ,  Mike Jahr ,  Milind Ganjoo ,  Parag Agrawal

IPC: G06F16/00 ,  G06F9/445 ,  G06F16/903 ,  H04L9/40 ,  G06F21/55 ,  G06F16/9032 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08 ,  G06Q50/00

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

公开(公告)号：US20200257543A1

公开(公告)日：2020-08-13

申请号：US15929375

申请日：2020-04-29

Applicant: Twitter, Inc.

Inventor： Sean Moon ,  Arvind Thiagarajan ,  Mike Jahr ,  Milind Ganjoo ,  Parag Agrawal

IPC: G06F9/445 ,  G06N20/00 ,  G06F16/9032 ,  G06F21/55 ,  H04L29/06 ,  G06N3/08 ,  G06F16/903

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.

公开(公告)号：US20180046918A1

公开(公告)日：2018-02-15

申请号：US15675671

申请日：2017-08-11

Applicant: Twitter, Inc.

Inventor： Sean Moon ,  Arvind Thiagarajan ,  Mike Jahr ,  Milind Ganjoo ,  Parag Agrawal

IPC: G06N3/08 ,  G06F17/30

CPC classification number: G06F9/44589 ,  G06F9/44552 ,  G06F16/90324 ,  G06F16/90335 ,  G06F21/552 ,  G06N3/08 ,  G06N20/00 ,  G06Q50/01 ,  H04L63/1433

Abstract: An example system includes a memory store of aggregate definitions. Each aggregate definition specifies a key value, an output store, a feature, a half-life value, and an aggregate operation metric to apply to a cross of the feature and the half-life value to generate aggregate metrics. The system also includes an aggregation engine that generates aggregate feature records from the input source based on the aggregate definitions and stores the aggregate feature records in the output store. An aggregate feature record includes an aggregate of the metric for the feature decayed over time using the half-life. The system also includes a query service that identifies, using the aggregate definitions, responsive aggregate feature records that satisfy parameters of a received request, applies the half-life to the responsive feature records, and provides the responsive feature records to a requester, the requester using the responsive feature records as input for a neural network.