-
公开(公告)号：US10482884B1
公开(公告)日：2019-11-19
申请号：US15663514
申请日：2017-07-28
Applicant: Amazon Technologies, Inc.
Inventor： Jeff Bradley Beal , Kevin Robert Charter , Ajay Gopalakrishnan , Sumedha Arvind Kshirsagar , Nishant Kumar
Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform multiple actions corresponding to this intent. The platform may select a target action to perform, and may engage in a back-and-forth dialog to obtain information for completing the target action. The action may include streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user.
-
公开(公告)号：US09053118B1
公开(公告)日：2015-06-09
申请号：US13924371
申请日：2013-06-21
Applicant: Amazon Technologies, Inc.
Inventor： Roy N. Harkness , Paul A. Larpenteur , Ajay Gopalakrishnan , Hubert Wong
CPC classification number: H04N19/86 , G06F17/3012 , G06T3/0056 , G06T3/4007 , G06T3/4023 , G06T5/002 , G06T5/003 , H04N1/393
Abstract: Systems and methods are provided for processing images (or other such instances of content) to detect which of the images exhibit artifacts when modified, such as by applying standard transformation algorithms to modify the images. Such techniques enable transformation algorithms to be applied to the detected images to minimize or prevent artifacts. In some embodiments, the headers of the detected images can be tagged with transformative instructions that indicate which transformation algorithms to apply. Responsive to a request from a web client to modify and render one of the detected images, embodiments obtain the requested image, read the transformative instructions in the header, apply the transformation algorithm specified in the header to modify the image so as to minimize or prevent artifacts, and render the modified image.
Abstract translation: 提供的系统和方法用于处理图像（或其他内容的其它这样的实例）以检测哪些图像在修改时显示伪像，例如通过应用标准变换算法来修改图像。 这样的技术使得能够将变换算法应用于检测到的图像以最小化或防止伪像。 在一些实施例中，可以用指示应用哪些变换算法的变换指令来标记检测到的图像的标题。 响应于来自网络客户端的请求以修改和呈现所检测到的图像之一，实施例获得所请求的图像，读取标题中的变换指令，应用标题中指定的变换算法来修改图像，以便最小化或防止 工件，并渲染修改后的图像。
-
公开(公告)号：US11922925B1
公开(公告)日：2024-03-05
申请号：US16035977
申请日：2018-07-16
Applicant: Amazon Technologies, Inc.
Inventor： Peter Paul Henri Carbon , Vikram Kumar Gundeti , Frederic Johan Georges Deramat , Ajay Gopalakrishnan , John Daniel Thimsen
CPC classification number: G10L15/00 , G10L15/22 , G10L21/06 , G10L15/1815 , G10L2015/223
Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. In some instances, the speech recognition platform engages in a back-and-forth dialog with the user in order to properly fulfill the user's request.
-
Patent Agency Ranking
公开(公告)号：US11860942B1
公开(公告)日：2024-01-02
申请号：US15595688
申请日：2017-05-15
Applicant: Amazon Technologies, Inc.
Inventor： Omer Baluch , Julio Delgado Mangas , Kiran-Kumar Muniswamy Reddy , Ajay Gopalakrishnan , Antoun Joubran Kanawati , Si Yin , Mukul Vijay Karnik , Vishal Parakh , Timothy Andrew Rath , Bhupinder Singh Sidana , Jared Scott Lundell
IPC: G06F16/9032 , G06N20/00 , G06F16/33 , G06F16/48 , G06F16/35 , G06F16/955 , G06N5/01
CPC classification number: G06F16/90324 , G06F16/33 , G06F16/355 , G06F16/48 , G06F16/955 , G06N5/01 , G06N20/00
Abstract: Prediction logic analyzes previous data usage activities of a customer process running on a host machine to generate a first prediction indicating that the customer process will request a first data set at a first time. The prediction logic retrieves the first data set from long-term storage and loads the first data set into memory on the host machine in advance of the first time in order to provide the customer process with access to first data set in the memory during a period between the first time and a second time. The prediction logic further generates a second prediction indicating that the customer process will not access the first data set for a threshold period of time after the second time and stores the first data set in the long-term storage at the second time.
-
公开(公告)号：US20230410816A1
公开(公告)日：2023-12-21
申请号：US18341224
申请日：2023-06-26
Applicant: Amazon Technologies, Inc.
Inventor： Nishant Kumar , David Robert Thomas , Sumedha Arvind Kshirsagar , Vikas Jain , Jeff Bradley Beal , Ajay Gopalakrishnan , Shishir Sridhar Bharathi
IPC: G10L17/00 , G10L15/22 , G10L15/183 , G10L15/18
CPC classification number: G10L17/00 , G10L15/22 , G10L15/183 , G10L15/18 , G10L2015/228 , G10L2015/223
Abstract: Features are disclosed for performing functions in response to user requests based on contextual data regarding prior user requests. Users may engage in conversations with a computing device in order to initiate some function or obtain some information. A dialog manager may manage the conversations and store contextual data regarding one or more of the conversations. Processing and responding to subsequent conversations may benefit from the previously stored contextual data by, e.g., reducing the amount of information that a user must provide if the user has already provided the information in the context of a prior conversation. Additional information associated with performing functions responsive to user requests may be shared among applications, further improving efficiency and enhancing the user experience.
-
公开(公告)号：US10026394B1
公开(公告)日：2018-07-17
申请号：US13843392
申请日：2013-03-15
Applicant: Amazon Technologies, Inc.
Inventor： Peter Paul Henri Carbon , Vikram Kumar Gundeti , Frederic Johan Georges Deramat , Ajay Gopalakrishnan , John Daniel Thimsen
Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. In some instances, the speech recognition platform engages in a back-and-forth dialog with the user in order to properly fulfill the user's request.
-
公开(公告)号：US09754591B1
公开(公告)日：2017-09-05
申请号：US14083332
申请日：2013-11-18
Applicant: Amazon Technologies, Inc.
Inventor： Nishant Kumar , David Robert Thomas , Sumedha Arvind Kshirsagar , Vikas Jain , Jeff Bradley Beal , Ajay Gopalakrishnan , Shishir Sridhar Bharathi
IPC: G10L15/18 , G10L17/00 , G10L15/22 , G10L15/183
CPC classification number: G10L17/005 , G10L15/18 , G10L15/183 , G10L15/22 , G10L2015/223 , G10L2015/228
Abstract: Features are disclosed for performing functions in response to user requests based on contextual data regarding prior user requests. Users may engage in conversations with a computing device in order to initiate some function or obtain some information. A dialog manager may manage the conversations and store contextual data regarding one or more of the conversations. Processing and responding to subsequent conversations may benefit from the previously stored contextual data by, e.g., reducing the amount of information that a user must provide if the user has already provided the information in the context of a prior conversation. Additional information associated with performing functions responsive to user requests may be shared among applications, further improving efficiency and enhancing the user experience.
-
公开(公告)号：US09374601B1
公开(公告)日：2016-06-21
申请号：US14724650
申请日：2015-05-28
Applicant: AMAZON TECHNOLOGIES, INC.
Inventor： Roy N. Harkness , Paul A. Larpenteur , Ajay Gopalakrishnan , Hubert Wong
CPC classification number: H04N19/86 , G06F17/3012 , G06T3/0056 , G06T3/4007 , G06T3/4023 , G06T5/002 , G06T5/003 , H04N1/393
Abstract: Systems and methods are provided for processing images (or other such instances of content) to detect which of the images exhibit artifacts when modified, such as by applying standard transformation algorithms to modify the images. Such techniques enable transformation algorithms to be applied to the detected images to minimize or prevent artifacts. In some embodiments, the headers of the detected images can be tagged with transformative instructions that indicate which transformation algorithms to apply. Responsive to a request from a web client to modify and render one of the detected images, embodiments obtain the requested image, read the transformative instructions in the header, apply the transformation algorithm specified in the header to modify the image so as to minimize or prevent artifacts, and render the modified image.
Abstract translation: 提供的系统和方法用于处理图像（或其他内容的其它这样的实例）以检测哪些图像在修改时显示伪像，例如通过应用标准变换算法来修改图像。 这样的技术使得能够将变换算法应用于检测到的图像以最小化或防止伪像。 在一些实施例中，可以用指示应用哪些变换算法的变换指令来标记检测到的图像的标题。 响应于来自网络客户端的请求以修改和呈现所检测到的图像之一，实施例获得所请求的图像，读取标题中的变换指令，应用标题中指定的变换算法来修改图像，以便最小化或防止 工件，并渲染修改后的图像。
-
-
-
-
-
-
-
Search Results
18
records
(took 0.021 seconds)
