公开(公告)号：US11216745B2

公开(公告)日：2022-01-04

申请号：US15805484

申请日：2017-11-07

Applicant: Google LLC

Inventor： Sandro Feuz ,  Victor Carbune

IPC: G06N5/02 ,  G06N20/00 ,  G06F9/46

Abstract: The present disclosure provides systems and methods for on-device machine learning. In particular, the present disclosure is directed to an on-device machine learning platform and associated techniques that enable on-device prediction, training, example collection, and/or other machine learning tasks or functionality. The on-device machine learning platform can include a mode controller that allows a user to provide data input indicating whether to operate one or more applications on the device in a first collection mode (e.g., permission mode) for storing training examples or a second collection mode for (e.g., incognito mode) for not storing training examples. The training examples can be generated based on user interaction with the one or more applications and used to personalize one or more machine-learned models used by the application(s) by retraining the models using the user-specific training examples.

公开(公告)号：US20210385557A1

公开(公告)日：2021-12-09

申请号：US17282492

申请日：2019-07-23

Applicant: Google LLC

Inventor： Victor Carbune ,  Andrii Maksai ,  Sandro Feuz

IPC: H04N21/8541 ,  H04N21/845 ,  H04N21/8545 ,  H04N21/8405

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, identify and classify the various video pathways in an interactive video based on the content of these video pathways. A video comprising multiple video segments is obtained from a video library. Each video segment is directly linked to at least one other video segment and the multiple video segments comprise a beginning segment, intermediate segments (including interactive segments), and final segments. Multiple video pathways in the video are identified. For each identified video pathway, classification data is generated and each such video pathway is then stored in the video library. When the video is selected from a particular category of the video library, the video segments of a video pathway that has a classification which is the same as the classification associated with the particular category, is then displayed.

公开(公告)号：US11178093B2

公开(公告)日：2021-11-16

申请号：US16553357

申请日：2019-08-28

Applicant: GOOGLE LLC

Inventor： Victor Carbune ,  Thomas Deselaers

IPC: H04L12/00 ,  H04L12/58 ,  G06F16/245 ,  H04L29/08

Abstract: The disclosure provides technology for adaptively creating and adjusting reminder notifications for a first user based on activity of a second user. An example method includes identifying an electronic message transmitted between a first user device and a second user device; accessing data associated with a user of the second device, wherein the data comprises activity state data for the user; determining a notification time for the first device based on the data associated with the user of the second device; and updating a reminder related to the electronic message based on the notification time.

公开(公告)号：US20210201051A1

公开(公告)日：2021-07-01

申请号：US17138866

申请日：2020-12-30

Applicant: GOOGLE LLC

Inventor： Thomas Deselaers ,  Victor Carbune

IPC: G06K9/00 ,  G06K9/62 ,  G06N20/00 ,  B60W30/18

Abstract: To selecting a lane in a multi-lane road segment for a vehicle travelling on the road segment, a system determines current traffic information for the road segment including a plurality of lanes and applies the current traffic information to a machine learning (ML) model to generate an indication of one of the plurality of lanes in which the vehicle is to travel. Subsequently to the vehicle selecting the indicated lane, the system determines an amount of time the vehicle took to travel a certain distance following the selection, and provides the determined amount of time to the ML model as a feedback signal.

公开(公告)号：US20210064921A1

公开(公告)日：2021-03-04

申请号：US16552253

申请日：2019-08-27

Applicant: Google LLC

Inventor： Victor Carbune ,  Alexandru-Marian Damian

IPC: G06K9/62 ,  G06F17/27 ,  G06F17/28 ,  G06N20/00 ,  G06N3/08

Abstract: A computing system can include one or more machine-learned models configured to receive context data that describes one or more entities to be named. In response to receipt of the context data, the machine-learned model(s) can generate output data that describes one or more names for the entity or entities described by the context data. The computing system can be configured to perform operations including inputting the context data into the machine-learned model(s). The operations can include receiving, as an output of the machine-learned model(s), the output data that describes the name(s) for the entity or entities described by the context data. The operations can include storing at least one name described by the output data.

公开(公告)号：US20210064624A1

公开(公告)日：2021-03-04

申请号：US16621109

申请日：2019-06-25

Applicant: Google LLC

Inventor： Victor Carbune ,  Sandro Feuz

IPC: G06F16/2455 ,  G06F16/901 ,  G06F16/953 ,  G06N20/00

Abstract: Techniques and a framework are described herein for gathering information about developing events from multiple live data streams and pushing new pieces of information to interested individuals as those pieces of information are learned. In various implementations, a plurality of live data streams may be monitored. Based on the monitoring, a data structure that models diffusion of information through a population may be generated and applied as input across a machine learning model to generate output. The output may be indicative of a likelihood of occurrence of a developing event and/or a predicted measure of relevancy of the developing event to a particular user. Based on a determination that the likelihood and/or measure of relevancy satisfies a criterion, one or more computing devices may render, as output, information about the developing event.

公开(公告)号：US20200154236A1

公开(公告)日：2020-05-14

申请号：US16618213

申请日：2018-10-30

Applicant: Google LLC

Inventor： Victor Carbune ,  Sandro Feuz

IPC: H04W4/02 ,  H04W4/029 ,  H04W4/80 ,  G06K9/62 ,  G11B20/10 ,  G06N20/00 ,  H04W4/38

Abstract: A method includes receiving an indication that a recording event has been initiated on an initial computing device responsive to an input from a user, the initial computing device including an initial sensor recording first sensor data during the recording event. The method also includes, responsive to the indication of the initiation of the recording event, identifying, based on a respective proximity to the initial computing device of each computing device from a plurality of other computing devices associated with the user, one or more additional computing devices from the plurality of other computing devices, each computing device including at least one respective sensor device, and transmitting, to the one or more additional computing devices, an activation command that causes the one or more additional computing devices to activate the at least one respective sensor device which initiates capturing of second sensor data during the recording event.

公开(公告)号：US10521655B1

公开(公告)日：2019-12-31

申请号：US16272610

申请日：2019-02-11

Applicant: Google LLC

Inventor： Victor Carbune ,  Thomas Deselaers

IPC: G06K9/00 ,  G06K9/34 ,  G06F16/38 ,  G06F16/383 ,  G06N20/00

Abstract: Implementations described herein determine, for a given document generated by a given source, one or more portions of content (e.g., phrase(s), image(s), paragraph(s), etc.) of the given document that may be influenced by bias of the given source. Further, implementations determine one or more additional resources that are related to the given source and that are related to the portion(s) of content of the given document. Yet further, implementations utilize the additional resource(s) to determine additional content that provides context for the portion(s) that may be influenced by bias. A relationship, between the additional resource(s) and the portions of the given document, can be defined. Based on the relationship being defined, the additional content can be caused to be rendered at a client device in response to the client device accessing the given document.

公开(公告)号：US20190325864A1

公开(公告)日：2019-10-24

申请号：US15954174

申请日：2018-04-16

Applicant: Google LLC

Inventor： Pedro Gonnet Anders ,  Victor Carbune ,  Daniel Keysers ,  Thomas Deselaers ,  Sandro Feuz

IPC: G10L15/18 ,  G10L15/19 ,  G10L15/22

Abstract: Techniques are described herein for enabling an automated assistant to adjust its behavior depending on a detected age range and/or “vocabulary level” of a user who is engaging with the automated assistant. In various implementations, data indicative of a user's utterance may be used to estimate one or more of the user's age range and/or vocabulary level. The estimated age range/vocabulary level may be used to influence various aspects of a data processing pipeline employed by an automated assistant. In various implementations, aspects of the data processing pipeline that may be influenced by the user's age range/vocabulary level may include one or more of automated assistant invocation, speech-to-text (“STT”) processing, intent matching, intent resolution (or fulfillment), natural language generation, and/or text-to-speech (“TTS”) processing. In some implementations, one or more tolerance thresholds associated with one or more of these aspects, such as grammatical tolerances, vocabularic tolerances, etc., may be adjusted.

公开(公告)号：US10397163B2

公开(公告)日：2019-08-27

申请号：US15345328

申请日：2016-11-07

Applicant: Google LLC

Inventor： Victor Carbune ,  Thomas Deselaers ,  Daniel M. Keysers

IPC: G06F15/16 ,  H04L12/58 ,  H04L29/08 ,  G06Q50/00 ,  G16H20/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium for implementing one or more application programming interfaces (APIs) that configure applications stored in an electronic device are described. An application may be configured to receive event information from various sources based on user preferences and application permissions. In response to receiving the event information, the app may determine whether a notification should be issued to a user. This determination may be made based on various factors such as the type of event, user history, contextual data, ranking data, and application permissions. The notifications may include one or more of messages to the user and recommended actions for consideration by the user. The actions may include sharing data with other users who share a presence or interest in an event with the user.