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：US11341331B2

公开(公告)日：2022-05-24

申请号：US16593724

申请日：2019-10-04

Applicant: Microsoft Technology Licensing, LLC

Inventor： Huakai Liao ,  Priyanka Vikram Sinha ,  Kevin Dara Khieu ,  Derek Martin Johnson ,  Siliang Kang ,  Huey-Ru Tsai ,  Amit Srivastava

IPC: G06F40/289 ,  G10L15/18 ,  G06N3/08 ,  G06K9/00 ,  G10L15/22 ,  G06F40/106 ,  G06F40/211 ,  G06V40/10 ,  G06V40/16

Abstract: An intelligent speech assistant receives information collected while a user is speaking. The information can comprise speech data, vision data, or both, where the speech data is from the user speaking and the vision data is of the user while speaking. The assistant evaluates the speech data against a script which can contain information that the user should speak, information that the user should not speak, or both. The assistant collects instances where the user utters phrases that match the script or instances where the user utters phrases that do not match the script, depending on whether phases should or should not be spoken. The assistant evaluates vision data to identify gestures, facial expressions, and/or emotions of the user. Instances where the gestures, facial expressions, and/or emotions are not appropriate to the context are flagged. Real-time prompts and/or a summary is presented to the user as feedback.

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：US20170220232A1

公开(公告)日：2017-08-03

申请号：US15332114

申请日：2016-10-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael Jay Gilmore ,  Kerry Young ,  Lei Shi ,  Alexandre Gueniot ,  Derek Martin Johnson ,  Jing Zhao ,  Charles Cummins ,  Aviral Ajit ,  Paul Scuderi

IPC: G06F3/0484 ,  G06F9/44 ,  G06F3/16

CPC classification number: G06F3/04845 ,  G06F3/0483 ,  G06F3/0485 ,  G06F3/0488 ,  G06F3/04883 ,  G06F3/167 ,  G06F9/451 ,  G06F2203/04806

Abstract: Technology is disclosed herein that enhances the user experience with presentation programs and the operational aspects of such programs. In an implementation, a presentation program includes a hierarchy of parent slides and child slides in a collection of slides. Navigating from a parent slide to a child slide triggers a contextual zoom-in transition into the child slide. Navigating back to the parent slide from the child slide triggers a contextual zoom-out transition to the parent slide. Other non-limiting examples describe smart slide functionality of an exemplary presentation program. A smart slide is a slide of a slide deck that comprises one or more slide links, which provide an active link to another slide of the slide deck.

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

IPC: G06V20/40 ,  G06N20/00 ,  G06V40/16 ,  G06V40/20

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：US10754508B2

公开(公告)日：2020-08-25

申请号：US15332196

申请日：2016-10-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael Jay Gilmore ,  Kerry Young ,  Lei Shi ,  Charles Cummins ,  Lauren Michelle Janas ,  Derek Martin Johnson ,  Paul Scuderi

IPC: G06F3/0483 ,  G06F16/40 ,  G06F16/438 ,  G06F9/451 ,  G06F3/0482 ,  G06F16/25 ,  G06F3/0484

Abstract: In a non-limiting example of the present disclosure, an exemplary table of contents slide may be displayed for a slide deck of a presentation program. The table of contents slide may comprise one or more sections of grouped slides for the slide deck. A selection of a section link may be received. The section link links the table of contents slide to a section of grouped slides. An exemplary presentation program may navigate the slide deck to a first slide of the section based on the received selection. When the navigation of the section is completed, the presentation program returns the slide deck to one of: the table of contents slide and the first slide of the section. Other examples described relate to creation and rendering of an exemplary table of contents slide and/or section links within an exemplary table of contents slide of a presentation program.

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：US11494396B2

公开(公告)日：2022-11-08

申请号：US17152193

申请日：2021-01-19

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ji Li ,  Amit Srivastava ,  Muin Barkatali Momin ,  Muqi Li ,  Emily Lauren Tohir ,  SivaPriya Kalyanaraman ,  Derek Martin Johnson

IPC: G06F16/248 ,  G06F16/242 ,  G06F16/93 ,  G06F16/2457 ,  G06N3/02

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 a user query for creating content in a content generation application and determining an action from an intent of the user query. A prompt is generated based on the action and provided to a natural language generation model. In response to the prompt, output is received from the natural language generation model. Response content is generated based on the output in a format compatible with the content generation application. At least some of the response content is displayed to the user. The user can choose to keep, edit, or discard the response content. The user can iterate with additional queries until the content document reflects the user's desired content.

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

IPC: H04M3/56 ,  H04L12/18 ,  H04L29/06 ,  G06N3/08

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：US20210097133A1

公开(公告)日：2021-04-01

申请号：US16585441

申请日：2019-09-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Huakai Liao ,  Debapriya Pal ,  Sun Mao ,  Erik Thomas Oveson ,  Huitian Jiao ,  Daniel M Cheung ,  Derek Martin Johnson ,  Bogdan Popp

IPC: G06F17/21 ,  G06K9/62 ,  G06N20/00 ,  G06F11/34 ,  G06F17/24

Abstract: A system and method for personalizing a display of a recommendation in a user interface element of an application is described. The system accesses application activities of a user of the application. A user preference is formed based on the application activities. The system identifies a context of a current activity of the application and generates a content recommendation in the application based on the context of the current activity of the application and the user preference.