-
公开(公告)号：US12032922B2
公开(公告)日：2024-07-09
申请号：US17318170
申请日：2021-05-12
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ji Li , Konstantin Seleskerov , Huey-Ru Tsai , Muin Barkatali Momin , Ramya Tridandapani , Sindhu Vigasini Jambunathan , Amit Srivastava , Derek Martin Johnson , Gencheng Wu , Sheng Zhao , Xinfeng Chen , Bohan Li
IPC: G06F40/58 , G06F3/0481 , G06F16/2457 , G06F40/205 , G10L13/02
CPC classification number: G06F40/58 , G06F3/0481 , G06F16/24578 , G06F40/205 , G10L13/02
Abstract: Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving an input document and parsing the input document to generate inputs for a natural language generation model using a text analysis model. The natural language generation model generates one or more candidate presentation scripts based on the inputs. A presentation script is selected from the candidate presentation scripts and displayed. A text-to-speech model may be used to generate a synthesized audio presentation of the presentation script. A final presentation may be generated that includes a visual display of the input document and the corresponding audio presentation in sync with the visual display.
-
公开(公告)号：US11909922B2
公开(公告)日：2024-02-20
申请号：US18155918
申请日：2023-01-18
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ji Li , Amit Srivastava , Derek Martin Johnson , Priyanka Vikram Sinha , Konstantin Seleskerov , Gencheng Wu
IPC: H04M3/56 , G06N3/08 , H04L12/18 , H04L65/401 , H04L65/403
CPC classification number: H04M3/568 , G06N3/08 , H04L12/1818 , H04L12/1822 , H04L65/403 , H04L65/4015
Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals. Further examples described herein extend to training and application of artificial intelligence (AI) processing, in real-time (or near real-time), that is configured to automatically analyze acoustic features of audio streams and automatically generate exemplary reaction indications.
-
公开(公告)号：US20170068693A1
公开(公告)日：2017-03-09
申请号：US14845978
申请日：2015-09-04
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.
Inventor： Azmil Macksood , Aleksei Nikolaevich Triastcyn , Konstantin Seleskerov , Vidar Tveoy Knudsen , Panos Sakkos
IPC: G06F17/30
CPC classification number: G06F16/2228 , G06F16/248 , G06F16/907 , G06F16/951 , G06F16/9562 , G06F16/9566 , G06F16/972
Abstract: Exposing content to individuals in an enterprise is provided. An external content sharing system includes a graph server comprising an API engine, a graph index, and an activity processing and analytics engine. When a user selects to share external content via a user agent, the API engine receives an API call including a URL of the external content from the user agent. The API engine accesses the content, extracts metadata, and stores the metadata as a node in the graph index, where connections are made between the node and individuals who are socially close to the user. The API engine receives a query request for content associated with an individual socially close to the user, queries the graph index, and provides a result including the metadata of the external content and the URL for generating and exposing a visual information element representative of the external content to the individual.
Abstract translation: 向企业内的个人披露内容。 外部内容共享系统包括包括API引擎，图表索引和活动处理和分析引擎的图形服务器。 当用户通过用户代理选择共享外部内容时，API引擎从用户代理接收包括外部内容的URL的API调用。 API引擎访问内容，提取元数据，并将元数据作为一个节点存储在图表索引中，其中节点与社交上接近用户的个人之间进行连接。 API引擎接收与与用户相近的个人相关联的内容的查询请求，查询图表索引，并提供包括外部内容的元数据和URL的结果，用于生成和公开表示外部的视觉信息元素 内容给个人。
-
Patent Agency Ranking
公开(公告)号：US12026948B2
公开(公告)日：2024-07-02
申请号：US17085755
申请日：2020-10-30
Applicant: Microsoft Technology Licensing, LLC
Inventor： Konstantin Seleskerov , Amit Srivastava , Derek Martin Johnson , Priyanka Vikram Sinha , Gencheng Wu , Brittany Elizabeth Mederos
CPC classification number: G06V20/41 , G06N20/00 , G06V20/46 , G06V40/176 , G06V40/23
Abstract: Techniques performed by a data processing system include establishing an online presentation session for conducting an online presentation, receiving first media streams comprising presentation content from the first computing device, receiving second media streams from the second computing devices of a subset of the plurality of participants, the second media streams including audio content, video content, or both of the subset of the plurality of participants, analyzing the first media streams using first machine learning models to generate feedback results, analyzing the set of second media streams to identify first reactions by the participants to obtain reaction information, automatically analyzing the feedback results and the reactions to identify discrepancies between the feedback results and the reactions, and automatically updating one or more parameters of the machine learning models based on the discrepancies to improve the suggestions for improving the online presentation.
-
公开(公告)号：US10394916B2
公开(公告)日：2019-08-27
申请号：US15263674
申请日：2016-09-13
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Alan Tus , Konstantin Seleskerov , Panos Sakkos , Rovin Bhandari
IPC: H04L29/06 , G06F16/9535
Abstract: Technologies are described to provide a personalized search environment to users without requiring enterprise environment access. Upon access of a personal service account such as one in a productivity service, a user's personal environment may be created by an aggregation service using graph based data infrastructure. Sources of information may include personal email accounts, calendars, social/professional networks, task list applications, online data storage services, health applications, gaming applications, and communication applications associated with the user. A personalized search application may then use the data from the aggregation service and/or (if available) user's enterprise account information to perform personalized searches with relevant results for the user.
-
公开(公告)号：US11570307B2
公开(公告)日：2023-01-31
申请号：US16983649
申请日：2020-08-03
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ji Li , Amit Srivastava , Derek Martin Johnson , Priyanka Vikram Sinha , Konstantin Seleskerov , Gencheng Wu
IPC: H04M3/56 , G06N3/08 , H04L12/18 , H04L65/401 , H04L65/403
Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals. Further examples described herein extend to training and application of artificial intelligence (AI) processing, in real-time (or near real-time), that is configured to automatically analyze acoustic features of audio streams and automatically generate exemplary reaction indications.
-
公开(公告)号：US20220038580A1
公开(公告)日：2022-02-03
申请号：US16983649
申请日：2020-08-03
Applicant: Microsoft Technology Licensing, LLC
Inventor： Ji Li , Amit Srivastava , Derek Martin Johnson , Priyanka Vikram Sinha , Konstantin Seleskerov , Gencheng Wu
Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals. Further examples described herein extend to training and application of artificial intelligence (AI) processing, in real-time (or near real-time), that is configured to automatically analyze acoustic features of audio streams and automatically generate exemplary reaction indications.
-
公开(公告)号：US20180075148A1
公开(公告)日：2018-03-15
申请号：US15263674
申请日：2016-09-13
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Alan Tus , Konstantin Seleskerov , Panos Sakkos , Rovin Bhandari
CPC classification number: G06F16/9535 , H04L63/08 , H04L63/102
Abstract: Technologies are described to provide a personalized search environment to users without requiring enterprise environment access. Upon access of a personal service account such as one in a productivity service, a user's personal environment may be created by an aggregation service using graph based data infrastructure. Sources of information may include personal email accounts, calendars, social/professional networks, task list applications, online data storage services, health applications, gaming applications, and communication applications associated with the user. A personalized search application may then use the data from the aggregation service and/or (if available) user's enterprise account information to perform personalized searches with relevant results for the user.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.017 seconds)
