公开(公告)号：US20230350909A1

公开(公告)日：2023-11-02

申请号：US18350685

申请日：2023-07-11

Applicant: Google LLC

Inventor： Emanuel Taropa

IPC: G06F16/248 ,  G06F16/28 ,  G06F16/22 ,  G06F16/2455 ,  G06F16/2458

CPC classification number: G06F16/248 ,  G06F16/285 ,  G06F16/2228 ,  G06F16/2455 ,  G06F16/2477 ,  G06F16/2474 ,  G06F16/2465

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. One of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.

公开(公告)号：US20240311402A1

公开(公告)日：2024-09-19

申请号：US18136634

申请日：2023-04-19

Applicant: GOOGLE LLC

Inventor： Martin Baeuml ,  Yanping Huang ,  Wenhao Jia ,  Chang Lan ,  Yuanzhong Xu ,  Junwhan Ahn ,  Alexander Bailey ,  Leif Schelin ,  Trevor Strohman ,  Emanuel Taropa ,  Sidharth Mudgal ,  Yanyan Zheng ,  Zhifeng Chen ,  Ahmad Beirami

IPC: G06F16/332 ,  G06F40/40

CPC classification number: G06F16/3322 ,  G06F16/3329 ,  G06F40/40

Abstract: Implementations relate to reducing latency in generating and/or rendering natural language (NL) output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, and generate the NL based output utilizing the LLM. The NL based output can be a stream of NL based output in that it includes a plurality of segments, and is generated on a segment-by-segment basis. In some implementations, a first segment of the stream of NL based output is selected for inclusion in the stream of NL based output as a second segment (and any subsequent segment) is being generated to reduce latency in evaluating the NL based output as a whole prior to rendering thereof. In some versions of those implementations, the first segment is rendered as the second segment (and any subsequent segment) is being generated to further reduce latency in rendering thereof.

公开(公告)号：US11188603B2

公开(公告)日：2021-11-30

申请号：US16586634

申请日：2019-09-27

Applicant: GOOGLE LLC

Inventor： Ralitsa Lyudmilova Angelova ,  Jean-Yves Delort ,  Pete Richard Lidwell ,  Emanuel Taropa ,  Yaxin Liu ,  Tomasz Kaftal

IPC: G06F16/9535 ,  G06F16/435 ,  G06Q30/02 ,  H04L12/26

Abstract: A method for identifying products associated with items of content, including: receiving, by a server from a first client device, a first request for a first item of content; retrieving, by the server from data storage, the first item of content in response to the first request for the first item of content; retrieving, by the server from data storage, an identification of an Internet search request transmitted by a second client device within a predetermined temporal window of playback of the first item of content by the second client device; retrieving, by the server from data storage, a second item of content selected in response to the Internet search request transmitted by the second client device; and providing, by the server to the first client device, the first and second items of content.

公开(公告)号：US20200026740A1

公开(公告)日：2020-01-23

申请号：US16586634

申请日：2019-09-27

Applicant: GOOGLE LLC

Inventor： Ralitsa Lyudmilova Angelova ,  Jean-Yves Delort ,  Pete Richard Lidwell ,  Emanuel Taropa ,  Yaxin Liu ,  Tomasz Kaftal

IPC: G06F16/9535 ,  G06F16/435 ,  G06Q30/02 ,  H04L12/26

Abstract: A method for identifying products associated with items of content, including: receiving, by a server from a first client device, a first request for a first item of content; retrieving, by the server from data storage, the first item of content in response to the first request for the first item of content; retrieving, by the server from data storage, an identification of an Internet search request transmitted by a second client device within a predetermined temporal window of playback of the first item of content by the second client device; retrieving, by the server from data storage, a second item of content selected in response to the Internet search request transmitted by the second client device; and providing, by the server to the first client device, the first and second items of content.

公开(公告)号：US10423638B2

公开(公告)日：2019-09-24

申请号：US15499398

申请日：2017-04-27

Applicant: Google LLC

Inventor： Emanuel Taropa

IPC: G06F16/00 ,  G06F16/248 ,  G06F16/28 ,  G06F16/22 ,  G06F16/2455 ,  G06F16/2458

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. One of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.