公开(公告)号：US20160357786A1

公开(公告)日：2016-12-08

申请号：US15240926

申请日：2016-08-18

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Justin Hamilton ,  Troy Ma ,  Kun Wu ,  Bing Lang ,  Xiaowei Sheng ,  Avinash Vemuluru ,  Paul Borza

IPC: G06F17/30

CPC classification number: G06F17/30268 ,  G06F17/30253 ,  G06F17/30265 ,  G06F17/3028 ,  G06F17/30286 ,  G06F17/3053

Abstract: A representative image system is described herein that provides a representative image for any given search query. Upon receiving a search for a term (or terms), the system accesses an inverted index to identify images associated with that term. The system then receives a ranked list of images. The ranked list includes image identifiers, and once an item in the list is selected the system can use the associated image identifier to retrieve the image from a thumbnail or other server. If an editor has overridden the default image for the present search query, then the system returns the image identifier for the overridden image, which can be used to access the image from the thumbnail or other server. Thus, the representative image system provides a reliable and universal mechanism for retrieving representative images for any given topic dynamically in real time.

公开(公告)号：US20230215441A1

公开(公告)日：2023-07-06

申请号：US17926291

申请日：2021-04-21

Applicant: Microsoft Technology Licensing, LLC

Inventor： Kun Wu

IPC: G10L17/22 ,  G10L17/18 ,  G10L17/14

CPC classification number: G10L17/22 ,  G10L17/18 ,  G10L17/14

Abstract: The present disclosure provides methods and apparatuses for providing prompts in speech recognition results in real time. A current speech input in an audio stream for a target event may be obtained. A current utterance text corresponding to the current speech input may be identified. A prompt may be generated based at least on the current utterance text, the prompt comprising at least one predicted subsequent utterance text sequence. A speech recognition result for the current speech input may be provided, the speech recognition result comprising the current utterance text and the prompt.

公开(公告)号：US11182408B2

公开(公告)日：2021-11-23

申请号：US16417902

申请日：2019-05-21

Applicant: Microsoft Technology Licensing, LLC

Inventor： Kun Wu ,  Yiran Shen ,  Houdong Hu ,  Soudamini Sreepada ,  Arun Sacheti ,  Mithun Das Gupta ,  Rushabh Rajesh Gandhi ,  Sudhir Kumar

IPC: G06F16/00 ,  G06F16/28 ,  G06F16/22 ,  G06F16/583 ,  G06F16/587 ,  G06F16/532

Abstract: A computer-implemented technique is described herein for using a machine-trained model to identify individual objects within images. The technique then creates a relational index for the identified objects. That is, each index entry in the relational index is associated with a given object, and includes a set of attributes pertaining to the given object. One such attribute identifies at least one latent semantic vector associated with the given object. Each attribute provides a way of linking the given object to one or more other objects in the relational index. In one application of this technique, a user may submit a query that specifies a query object. The technique consults the relational index to find one or more objects that are related to the query object. In some cases, the query object and each of the other objects have a complementary relationship.

公开(公告)号：US20190236416A1

公开(公告)日：2019-08-01

申请号：US15885518

申请日：2018-01-31

Applicant: Microsoft Technology Licensing, LLC

Inventor： Zhenghao Wang ,  Xuedong Huang ,  Lijuan Qin ,  Kun Wu ,  Huaming Wang

IPC: G06K9/62 ,  H04N5/232 ,  H04N5/262 ,  G06K9/00 ,  G10L17/22 ,  G06F3/16 ,  G06F3/01 ,  H04R1/22 ,  G06K7/14 ,  G06K7/10 ,  G06N3/08

CPC classification number: G06K9/6289 ,  G06F3/017 ,  G06F3/16 ,  G06F3/167 ,  G06K7/10722 ,  G06K7/1417 ,  G06K9/00288 ,  G06N3/08 ,  G10L17/22 ,  H04N5/23216 ,  H04N5/23238 ,  H04N5/2628 ,  H04N13/204 ,  H04R1/222 ,  H04R1/2892 ,  H04R2201/401

Abstract: In some embodiments, the disclosed subject matter involves a system and method relating to using an ambient capture device including a fisheye camera and a microphone array to capture audio and video in an environment, for use in an artificial intelligence (Al) application. The device with fisheye camera may provide approximately a 360° audio and video view, at relatively low cost. An embodiment may utilize a speech and vision fusion model component. The speech and vision fusion model may be trained using deep learning to combine features from many different sources, including available sensor data from the capture device. A long short term memory (LSTM) model may inter or identify features such as, but not limited to: audio direction; vision detection and tracking; voice signature; facial signature; gesture recognition; and object identification. The fusion processing may be performed by a cloud server, enabling the capture device to remain less complex.

公开(公告)号：US11947589B2

公开(公告)日：2024-04-02

申请号：US17710761

申请日：2022-03-31

Applicant: Microsoft Technology Licensing, LLC

Inventor： Li Huang ,  Rui Xia ,  Zhiting Chen ,  Kun Wu ,  Meenaz Merchant ,  Kamal Ginotra ,  Arun K. Sacheti ,  Chu Wang ,  Andrew Lawrence Stewart ,  Hanmu Zuo ,  Saurajit Mukherjee

IPC: G06F16/50 ,  G06F16/532 ,  G06F16/535 ,  G06F16/56

CPC classification number: G06F16/535 ,  G06F16/532 ,  G06F16/56

Abstract: Systems and methods directed to returning personalized image-based search results are described. In examples, a query including an image may be received, and a personalized item embedding may be generated based on the image and user profile information associated with a user. Further, a plurality of candidate images may be obtained based on the personalized item embedding. The candidate images may then be ranked according to a predicted level of user engagement for a user, and then diversified to ensure visual diversity among the ranked images. A portion of the diversified images may then be returned in response to an image-based search.

公开(公告)号：US10528572B2

公开(公告)日：2020-01-07

申请号：US14839385

申请日：2015-08-28

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Arun Sacheti ,  Yanfeng Sun ,  Aaron Chun Win Yuen ,  Parthasarathy Govindarajen ,  Kun Wu ,  Soohoon Cho ,  Malik Mehdi Pradhan ,  Alexandre Michelis ,  Gautam Vishwas Vaidya ,  Karim Amin Hasham ,  Avinash Vemuluru

IPC: G06F16/20 ,  G06F16/2457 ,  G06N20/00 ,  G06F16/248 ,  G06F16/9535

Abstract: The technology described herein provides an efficient mechanism for quickly analyzing huge amounts of media content to find media content (hereafter “content” or “media content”) that is relevant to a user. The technology analyzes features of a curator to classify curators by interest and/or find curators with similar content recommendations. The curator data can be used to make curator recommendations to users based on the user's interests. The technology described herein collects curator data from multiple content sites and analyzes the data to identify curators that recommend similar content on different content sites.

公开(公告)号：US09910867B2

公开(公告)日：2018-03-06

申请号：US15240926

申请日：2016-08-18

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Justin Hamilton ,  Troy Ma ,  Kun Wu ,  Bing Lang ,  Xiaowei Sheng ,  Avinash Vemuluru ,  Paul Borza

IPC: G06F17/30

CPC classification number: G06F17/30268 ,  G06F17/30253 ,  G06F17/30265 ,  G06F17/3028 ,  G06F17/30286 ,  G06F17/3053

Abstract: A representative image system is described herein that provides a representative image for any given search query. Upon receiving a search for a term (or terms), the system accesses an inverted index to identify images associated with that term. The system then receives a ranked list of images. The ranked list includes image identifiers, and once an item in the list is selected the system can use the associated image identifier to retrieve the image from a thumbnail or other server. If an editor has overridden the default image for the present search query, then the system returns the image identifier for the overridden image, which can be used to access the image from the thumbnail or other server. Thus, the representative image system provides a reliable and universal mechanism for retrieving representative images for any given topic dynamically in real time.

公开(公告)号：US20160150038A1

公开(公告)日：2016-05-26

申请号：US14572750

申请日：2014-12-16

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Arun Sacheti ,  Karim Hasham ,  Parthasarathy Govindarajen ,  Kun Wu ,  Gautam V. Vaidya ,  Anthony Tran ,  Shannon Westphal ,  Nan Wu ,  Ahmed Muneeb ,  Jane Jiyoon Park

IPC: H04L29/08

CPC classification number: H04L67/22 ,  G06F16/9535 ,  H04L67/025 ,  H04L67/306

Abstract: Systems, computing devices, and methods for efficiently surfacing information relating to an item of content to a user are presented. A process executing on a user's computing device monitors for a user indication to obtain related information regarding an item of content. Upon receiving the indication, the process formulates a request for the related information and submits the request to a content aggregation service. The content aggregation service identifies the content and extracts a plurality of attribute/value pairs from an aggregated content store regarding the subject matter of the item of content. The extracted information is returned to the requesting process as the related information, which is then presented to the user.

Abstract translation: 呈现用于向用户有效地显示与内容项有关的信息的系统，计算设备和方法。 在用户计算设备上执行的过程监视用户指示以获得关于内容项的相关信息。 在接收到该指示时，该过程对相关信息做出请求，并将该请求提交给内容聚合服务。 内容聚合服务识别内容，并从关于内容项目的主题的聚合内容存储提取多个属性/值对。 所提取的信息作为相关信息返回到请求进程，然后将其提供给用户。