公开(公告)号：US20240005089A1

公开(公告)日：2024-01-04

申请号：US18368405

申请日：2023-09-14

Applicant: Microsoft Technology Licensing, LLC

Inventor： Si Meng ,  Jinge Yao ,  Chin-Yew Lin ,  Zhang Li ,  Fangrong Chen ,  Tao Wu ,  Sun Mao ,  Vincent Etter ,  Genglin Huang ,  Jing Liu ,  Peter Kurt Allenspach ,  Bogdan Popp

IPC: G06F40/174 ,  G06F40/253 ,  G06F40/106

CPC classification number: G06F40/174 ,  G06F40/253 ,  G06F40/106

Abstract: The present disclosure provides method and apparatus for document auto-completion. In an aspect, an instruction for creating a document may be received. The document may be presented in response to the instruction, at least a first section in the document including content suggested according to context information associated with the document. An edit operation to the document may be received. Content suggested in response to the edit operation may be presented in at least a second section in the document. In another aspect, context information associated with completion of a document may be identified. Content of at least one section in the document may be generated, the content being suggested based at least on the context information. The content may be presented in the at least one section in the document.

公开(公告)号：US20230385320A1

公开(公告)日：2023-11-30

申请号：US17836456

申请日：2022-06-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： Weixin CAI ,  Si-Qing Chen ,  Michel Galley ,  William Brennan Dolan ,  Christopher J. Brockett ,  Zhang Li ,  Warren A. Aldred ,  Xinyu He ,  Jesse Alexander Freitas ,  Kaushik Ramaiah Narayanan

IPC: G06F16/338 ,  G06F16/332 ,  G06F16/335 ,  G06K9/62 ,  G06F40/30 ,  G06F40/253 ,  G06N20/00

CPC classification number: G06F16/338 ,  G06F16/3326 ,  G06F16/335 ,  G06K9/6215 ,  G06F40/30 ,  G06F40/253 ,  G06N20/00

Abstract: Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

公开(公告)号：US12105747B2

公开(公告)日：2024-10-01

申请号：US17836456

申请日：2022-06-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： Weixin Cai ,  Si-Qing Chen ,  Michel Galley ,  William Brennan Dolan ,  Christopher J. Brockett ,  Zhang Li ,  Warren A. Aldred ,  Xinyu He ,  Jesse Alexander Freitas ,  Kaushik Ramaiah Narayanan

IPC: G06F16/338 ,  G06F16/332 ,  G06F16/335 ,  G06F18/22 ,  G06F40/253 ,  G06F40/30 ,  G06N20/00

CPC classification number: G06F16/338 ,  G06F16/3326 ,  G06F16/335 ,  G06F18/22 ,  G06F40/253 ,  G06F40/30 ,  G06N20/00

Abstract: Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

公开(公告)号：US11636263B2

公开(公告)日：2023-04-25

申请号：US16890227

申请日：2020-06-02

Applicant: Microsoft Technology Licensing, LLC

Inventor： Zhang Li ,  Michael Wilson Daniels ,  Enrico Cadoni ,  Domenic Joseph Cipollone ,  Bhavuk Jain ,  Olivier Gauthier ,  Kaushik R. Narayanan ,  Siqing Chen ,  Alice Yingming Lai

IPC: G06F40/253 ,  G06N5/04 ,  G06N20/00

Abstract: An editor service receives a textual input. The editor service provides the textual input to a rule-based grammar checker to obtain a grammar checker result. The editor service also provides the textual input to a machine learning (ML) fluency model that checks the textual input for errors and provides a ML model result. The editor service aggregates the grammar checker result and the ML model result and generates an editor service output based upon the aggregated results. A representation of the editor service result is provided to the client computing system for surfacing through a user interface.

公开(公告)号：US12153893B2

公开(公告)日：2024-11-26

申请号：US17583909

申请日：2022-01-25

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tomasz Lukasz Religa ,  Zhang Li ,  Christine Lauren Mayer ,  Max Wang ,  Huitian Jiao ,  Weixin Cai ,  Cheng Yang ,  Christie Chan ,  Siqing Chen

IPC: G06F40/35 ,  G06F40/253 ,  G06F40/284 ,  G06N20/00

Abstract: A method and system for providing tone detection for a content may include receiving a request to detect a tone for a content, retrieving user data and data about the content, detecting a content environment for the content based on at least one of the user data and the data about the content, detecting the tone for the content based on the content and the content environment, inputting the content and the detected tone into a machine-learning (ML) model for modifying the tone from the detected tone to a modified tone, obtaining at least one rephrased content segment as an output from the ML model, the rephrased content segment modifying the tone of the content from the detected tone to the modified tone, and providing at least one of the detected tone or the at least one rephrased content segment for display.

公开(公告)号：US11797756B2

公开(公告)日：2023-10-24

申请号：US17435332

申请日：2019-04-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Si Meng ,  Jinge Yao ,  Chin-Yew Lin ,  Zhang Li ,  Fangrong Chen ,  Tao Wu ,  Sun Mao ,  Vincent Etter ,  Genglin Huang ,  Jing Liu ,  Peter Kurt Allenspach ,  Bogdan Popp

IPC: G06F17/00 ,  G06F40/174 ,  G06F40/253 ,  G06F40/106

CPC classification number: G06F40/174 ,  G06F40/106 ,  G06F40/253

Abstract: A method and apparatus may be used for document auto-completion. In an aspect, an instruction for creating a document may be received. The document may be presented in response to the instruction, at least a first section in the document including content suggested according to context information associated with the document. An edit operation to the document may be received. Content suggested in response to the edit operation may be presented in at least a second section in the document. In another aspect, context information associated with completion of a document may be identified. Content of at least one section in the document may be generated, the content being suggested based at least on the context information. The content may be presented in the at least one section in the document.

公开(公告)号：US11429779B2

公开(公告)日：2022-08-30

申请号：US16459576

申请日：2019-07-01

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Zhang Li ,  Domenic Joseph Cipollone ,  Maria Isabel Carpenter ,  Juhi Amitkumar Naik ,  Susan Michele Hendrich ,  Michael Wilson Daniels ,  William Brennan Dolan ,  Christopher Brian Quirk ,  Christopher John Brockett ,  Alice Yingming Lai

IPC: G06F40/166 ,  G06F3/0482 ,  G06K9/62 ,  G06F40/47 ,  G06F40/295

Abstract: A method and system for providing replacement text segments for a given text segment may include receiving a request to provide the replacement text segment for the text segment in the document, examining a content characteristic of the document, and examining at least one of user-specific information, organization-specific information, or non-linguistic features of the document, before identifying at least one replacement text segment for the text segment, via a machine translation system, based on the content characteristic of the document and at least one of the user-specific information, the organization-specific information, or the non-linguistic features of the document. The method and system may include providing the identified replacement text segment for display to a user, receiving an input indicating a user's selection of the identified replacement text segment, and upon receiving the input, replacing the text segment in the document with the identified replacement text segment.

公开(公告)号：US11126794B2

公开(公告)日：2021-09-21

申请号：US16381965

申请日：2019-04-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Zhang Li ,  Christopher John Brockett ,  William Brennan Dolan ,  Christopher Brian Quirk ,  Alice Yingming Lai ,  Susan Michele Hendrich ,  Olivier Gauthier ,  Kaushik Ramaiah Narayanan ,  Maria Isabel Carpenter ,  Juhi Amitkumar Naik ,  Michael Wilson Daniels

IPC: G06F40/20 ,  G06F40/253 ,  G06F40/166 ,  G06F40/30 ,  G06F3/0482

Abstract: A method for providing targeted rewrites can include receiving a selection of text in a file; generating a set of target rewrites of the selection of text, the set of target rewrites comprising: at least one phrase or sentence having semantic similarity to a phrase or sentence of the selection of text; and a style that corresponds to a particular target style, wherein a target style is a representative style for a genre, profession, or environment; and providing for selection one or more of the target rewrites of the set of target rewrites.

公开(公告)号：US12216674B2

公开(公告)日：2025-02-04

申请号：US18178653

申请日：2023-03-06

Applicant: Microsoft Technology Licensing, LLC

Inventor： Aleksey Aleksandrovich Sokolov ,  Utkarsh Garg ,  Siqing Chen ,  Warren Anthony Aldred ,  Saket Kumar ,  Cheng Yang ,  Bhavuk Jain ,  Mahaveer Bhavarlal Kothari ,  Alyssa Rachel Mayo ,  Tashfeen Ahmed ,  Zhang Li ,  Olivier Michel Nicolas Gauthier ,  Christine Lauren Mayer ,  Jesse Alexander Freitas

IPC: G06F7/00 ,  G06F16/245 ,  G06F16/248 ,  G06N20/00

Abstract: A data processing system includes: a processor; a memory containing programming instructions for execution by the processor; and a network interface for communicating with an Artificial Intelligence (AI) engine. The programming instructions include an application for generating written content, the application having a function to generate and submit a structured query regarding the written content to the AI engine to generate feedback on an assessed quality of the written content, the structured query structured to prompt for feedback in a variety of specified categories for the written content. The application further includes a user interface to display the feedback on the written content and provide an option to a user to implement the feedback to revise the written content.

公开(公告)号：US20220138410A1

公开(公告)日：2022-05-05

申请号：US17435332

申请日：2019-04-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Si Meng ,  Jinge YAO ,  Chin-Yew Lin ,  Zhang Li ,  Fangrong Chen ,  Tao Wu ,  Sun Mao ,  Vincent Etter ,  Genglin Huang ,  Jing LIU ,  Peter Kurt ALLENSPACH ,  Bogdan POPP

IPC: G06F40/174 ,  G06F40/253 ,  G06F40/106

Abstract: The present disclosure provides method and apparatus for document auto-completion. In an aspect, an instruction for creating a document may be received. The document may be presented in response to the instruction, at least a first section in the document including content suggested according to context information associated with the document. An edit operation to the document may be received. Content suggested in response to the edit operation may be presented in at least a second section in the document. In another aspect, context information associated with completion of a document may be identified. Content of at least one section in the document may be generated, the content being suggested based at least on the context information. The content may be presented in the at least one section in the document.