中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.015 seconds)

    Obtaining responsive information from multiple corpora
    1.
    发明授权
    Obtaining responsive information from multiple corpora 有权

    公开(公告)号：US11017037B2

    公开(公告)日：2021-05-25

    申请号：US15703205

    申请日：2017-09-13

    Applicant: Google Inc.

    Inventor： Mugurel Ionut Andreica ,  Vladimir Vuskovic ,  Gökhan Bakir ,  Marcin Nowak-Przygodzki

    IPC: G06F16/9535 ,  G06F3/16 ,  G10L15/18 ,  G06F16/332 ,  G10L13/00 ,  G10L15/22 ,  G10L25/51 ,  G06F9/451

    Abstract: Techniques are described herein for automated assistants that search various alternative corpora for information. In various implementations, a method may include receiving, by an automated assistant via an input component of a first client device, a free form input, wherein the free form input includes a request for specific information; searching a general purpose corpus of online documents to obtain a first set of candidate response(s) to the request for specific information; searching a user-specific corpus of active document(s) to obtain a second set of candidate response(s) to the request for specific information; comparing the first and second sets of candidate responses; based on the comparing, selecting a given response to the request for specific information from the first or second set; and providing, by the automated assistant, output indicative of the given response.

    SEARCHING AND TAGGING MEDIA STORAGE WITH A KNOWLEDGE DATABASE
    2.
    发明申请
    SEARCHING AND TAGGING MEDIA STORAGE WITH A KNOWLEDGE DATABASE 审中-公开

    公开(公告)号：US20190012360A1

    公开(公告)日：2019-01-10

    申请号：US14940551

    申请日：2015-11-13

    Applicant: Google Inc.

    Inventor： Shirley Gaw ,  Vladimir Vuskovic ,  Raul Marian Furnica

    IPC: G06F17/30

    Abstract: Implementations disclose tagging a content item with a knowledge database. A method includes determining, using a processing device, a content item to be tagged, determining, using the processing device, an identification that is associated with the content item, the identification from a knowledge database comprising a collection of structured data corresponding to topics, tagging, using the processing device, the content item with the identification from the knowledge database, and storing, using the processing device, the content item and the identification corresponding to the tagged content item in a tag database.

    Embeddable media upload object
    3.
    发明授权
    Embeddable media upload object 有权
    可嵌入媒体上传对象

    公开(公告)号：US09432417B2

    公开(公告)日：2016-08-30

    申请号：US13926998

    申请日：2013-06-25

    Applicant: Google Inc.

    Inventor： Vladimir Vuskovic ,  Jaroslaw Jerzy Wilkiewicz ,  Eric P. Lundberg ,  Jeffrey Alan Posnick

    IPC: H04L29/06 ,  H04N21/2743 ,  H04N21/4223 ,  H04N21/4782

    CPC classification number: H04L65/40 ,  H04N21/2743 ,  H04N21/4223 ,  H04N21/4782

    Abstract: A user device's browser receives a page from a publishing system and presents content of the page within a window. Instructions from a media hosting system cause a frame to be created within the window. The frame includes a media upload object from a media hosting system that has a different address domain that the publishing system. A communication channel is established between the window and the frame to allow messages to be exchanged. The media upload object allows a user to create a media item and upload it to the media hosting system. Throughout the process of creating and uploading the media item, the media upload object transmits one or more messages to the page via the communication channel. Based on the messages, the page responds to what is occurring within the frame.

    Abstract translation: 用户设备的浏览器从发布系统接收页面并在窗口内呈现页面的内容。 媒体托管系统的指令会导致在窗口内创建一个帧。 该帧包括来自媒体托管系统的媒体上传对象，其具有与发布系统不同的地址域。 在窗口和帧之间建立通信信道以允许交换消息。 媒体上传对象允许用户创建媒体项目并将其上传到媒体托管系统。 在创建和上传媒体项目的过程中，媒体上传对象通过通信信道向页面发送一个或多个消息。 根据消息，页面会响应帧内发生的内容。

    Proactive provision of new content to group chat participants
    6.
    发明授权
    Proactive provision of new content to group chat participants 有权

    公开(公告)号：US10742435B2

    公开(公告)日：2020-08-11

    申请号：US15637640

    申请日：2017-06-29

    Applicant: Google Inc.

    Inventor： Vladimir Vuskovic ,  Yariv Adan

    IPC: H04L12/58 ,  G06F16/00 ,  H04L12/18 ,  G06F40/40 ,  G06Q10/00 ,  G06Q10/06 ,  H04L29/06 ,  H04L29/08

    Abstract: Techniques are described herein for automated assistants that proactively provide content to participant(s) of multi-participant message exchange threads (e.g., group chats, audio and/or video calls in which oral messages are transcribed for analysis, etc.) based on signals such as individual participant profiles associated with participant(s). In various implementations, automated assistant(s) that may not be explicitly invoked may analyze content of a message exchange thread involving multiple human participants and/or document(s) associated with the message exchange thread. Based on the analyzing, the automated assistant(s) may identify topic(s) pertinent to the message exchange thread. Based on individual participant profiles associated with the participants, the automated assistant(s) may identify shared interest(s) of the participants. The automated assistant(s) may then select new content based both on the pertinent topic(s) and the shared interest(s) of the participants and proactively provide the new content to one or more of the participants.

    OBTAINING RESPONSIVE INFORMATION FROM MULTIPLE CORPORA
    7.
    发明申请
    OBTAINING RESPONSIVE INFORMATION FROM MULTIPLE CORPORA 审中-公开

    公开(公告)号：US20190005138A1

    公开(公告)日：2019-01-03

    申请号：US15703205

    申请日：2017-09-13

    Applicant: Google Inc.

    Inventor： Mugurel Ionut Andreica ,  Vladimir Vuskovic ,  Gökhan Bakir ,  Marcin Nowak-Przygodzki

    IPC: G06F17/30 ,  G06F3/16 ,  G10L15/18 ,  G10L25/51 ,  G10L13/00 ,  G10L15/22 ,  G06F9/44

    Abstract: Techniques are described herein for automated assistants that search various alternative corpora for information. In various implementations, a method may include receiving, by an automated assistant via an input component of a first client device, a free form input, wherein the free form input includes a request for specific information; searching a general purpose corpus of online documents to obtain a first set of candidate response(s) to the request for specific information; searching a user-specific corpus of active document(s) to obtain a second set of candidate response(s) to the request for specific information; comparing the first and second sets of candidate responses; based on the comparing, selecting a given response to the request for specific information from the first or second set; and providing, by the automated assistant, output indicative of the given response.

    EMBEDDABLE MEDIA UPLOAD OBJECT
    8.
    发明申请
    EMBEDDABLE MEDIA UPLOAD OBJECT 有权
    可嵌入媒体上传对象

    公开(公告)号：US20150135076A1

    公开(公告)日：2015-05-14

    申请号：US13926998

    申请日：2013-06-25

    Applicant: Google Inc.

    Inventor： Vladimir Vuskovic ,  Jaroslaw Jerzy Wilkiewicz ,  Eric P. Lundberg ,  Jeffrey Alan Posnick

    IPC: H04L29/06

    CPC classification number: H04L65/40 ,  H04N21/2743 ,  H04N21/4223 ,  H04N21/4782

    Abstract: A user device's browser receives a page from a publishing system and presents content of the page within a window. Instructions from a media hosting system cause a frame to be created within the window. The frame includes a media upload object from a media hosting system that has a different address domain that the publishing system. A communication channel is established between the window and the frame to allow messages to be exchanged. The media upload object allows a user to create a media item and upload it to the media hosting system. Throughout the process of creating and uploading the media item, the media upload object transmits one or more messages to the page via the communication channel. Based on the messages, the page responds to what is occurring within the frame.

    Abstract translation: 用户设备的浏览器从发布系统接收页面并在窗口内呈现页面的内容。 媒体托管系统的指令会导致在窗口内创建一个帧。 该帧包括来自媒体托管系统的媒体上传对象，其具有与发布系统不同的地址域。 在窗口和帧之间建立通信信道以允许交换消息。 媒体上传对象允许用户创建媒体项目并将其上传到媒体托管系统。 在创建和上传媒体项目的过程中，媒体上传对象通过通信信道向页面发送一个或多个消息。 根据消息，页面会响应帧内发生的内容。

    PROACTIVE PROVISION OF NEW CONTENT TO GROUP CHAT PARTICIPANTS
    9.
    发明申请
    PROACTIVE PROVISION OF NEW CONTENT TO GROUP CHAT PARTICIPANTS 审中-公开

    公开(公告)号：US20190007228A1

    公开(公告)日：2019-01-03

    申请号：US15637640

    申请日：2017-06-29

    Applicant: Google Inc.

    Inventor： Vladimir Vuskovic ,  Yariv Adan

    IPC: H04L12/18 ,  G06Q10/00 ,  G06F17/30 ,  G06F17/28

    Abstract: Techniques are described herein for automated assistants that proactively provide content to participant(s) of multi-participant message exchange threads (e.g., group chats, audio and/or video calls in which oral messages are transcribed for analysis, etc.) based on signals such as individual participant profiles associated with participant(s). In various implementations, automated assistant(s) that may not be explicitly invoked may analyze content of a message exchange thread involving multiple human participants and/or document(s) associated with the message exchange thread. Based on the analyzing, the automated assistant(s) may identify topic(s) pertinent to the message exchange thread. Based on individual participant profiles associated with the participants, the automated assistant(s) may identify shared interest(s) of the participants. The automated assistant(s) may then select new content based both on the pertinent topic(s) and the shared interest(s) of the participants and proactively provide the new content to one or more of the participants.

    Searching and tagging media storage with a knowledge database
    10.
    发明授权
    Searching and tagging media storage with a knowledge database 有权
    使用知识数据库搜索和标记媒体存储

    公开(公告)号：US09189528B1

    公开(公告)日：2015-11-17

    申请号：US13835116

    申请日：2013-03-15

    Applicant: Google Inc.

    Inventor： Shirley Gaw ,  Vladimir Vuskovic ,  Raul Marian Fumica

    IPC: G06F17/30

    CPC classification number: G06F17/30873 ,  G06F17/30554

    Abstract: A system and method for searching media storage with a knowledge database is provided. The system includes a search retrieving unit to retrieve a search request, an association retrieval unit to retrieve an association between a content item from the media storage and an identification from the knowledge database based on the search request, and an output unit to output data generated by the association retrieval unit. A method tagging a content item with a knowledge database includes determining the content item to be tagged, tagging the content item with an identification from the knowledge database, and storing the content item and the tagged identification in a tag database.

    Abstract translation: 提供了一种利用知识数据库搜索媒体存储的系统和方法。 该系统包括检索搜索请求的搜索检索单元，检索来自媒体存储器的内容项与基于搜索请求的来自知识数据库的识别之间的关联的关联检索单元，以及输出生成的数据的输出单元 由关联检索单元。 使用知识数据库标记内容项目的方法包括确定要标记的内容项目，使用来自知识数据库的标识来标记内容项目，以及将内容项目和标记的标识存储在标签数据库中。

Patent Agency Ranking