Microsoft Technology Licensing, LLC

Kaushik Ramaiah Narayanan

Zhang Li

Olivier Gauthier

William B Dolan

Christopher John Brockett

Domenic J Cipollone

Susan Michele Hendrich

Michael Wilson Daniels

Si-Qing Chen

Hany Grees Gerges

Alice Yingming Lai

Robert J Martin

Christopher Brian Quirk

Lei Cui

Kevin Roland Powell

Furu Wei

Tomasz Lukasz Religa

Max Wang

Michel Galley

Huitian Jiao

Kyle Matthew Von Haden

Alfredo R Arnaiz

Binay K Pathak

Enrico Cadoni

Siqing Chen

Jesse Alexander Freitas

Warren Anthony Aldred

Maria Isabel Carpenter

Ravi Mandliya

Tao Ge

Kevin Field

Kaili Xu

Bhavuk Jain

Juhi Amitkumar Naik

Weixin Cai

Xinyu He

Utsab Bose

Jerry Gibson

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.

Automatic content generation

A system and method for converting a document is described. The system accesses a document comprising one or more section breaks. The system detects sections of the text document demarked by the one or more section breaks and generates a section title metadata and a section summary metadata for each section of the plurality of sections. The system inserts the section title metadata and the section summary metadata at the corresponding section breaks in the text document. The system modifies the text document into slides. Each slide being formed for each section based on the corresponding section title metadata and the section summary metadata. The system generates a presentation document based on the slides.

Document conversion engine

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.

Using editor service to control orchestration of grammar checker and machine learned mechanism

The present disclosure relates to processing operations configured to provide, through an adapted user interface of an application/service, seamless application of autocorrection for an electronic document and provision of review insights into the autocorrections. In addition to applying autocorrections, processing described herein selectively determines when to apply an autocorrection (e.g., while a user is entering an input or after) and further highlights autocorrections, through a user interface, in a manner that instantly lets a user know that an autocorrection has occurred and/or what type of autocorrection is being applied. Moreover, an adapted user interface provides user interface features than enable access to an intelligent user interface menu that provides a user with feedback mechanisms to better understand the types of autocorrections that were made to their electronic document as well as improve processing efficiency for reversing an autocorrection and/or making further autocorrection changes to an electronic document.

Systems and methods for seamless application of autocorrection and provision of review insights through adapted user interface

Status-based reading and authoring assistance is provided. A status-based reading and authoring assistance feature can automatically determine a status of a user and automatically adapt reading and authoring tools provided for display based on the determined status. The status-based reading and authoring assistance feature provides the right reading and authoring tools at the right time, according to the current use of the application. During a user session with respect to a productivity application that includes status-based reading and authoring assistance, signals (e.g., user actions and context information) associated with a file can be received. A status regarding the use of the file can be determined using at least the signals. The status can comprise a reading status or an authoring status (or even a sub status). Reading and authoring tools provided for a display of the productivity application can be adapted based on the status during the user session.

Status-based reading and authoring assistance

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.

Targeted rewrites

The present disclosure relates to systems and methods that are configured to semi-automate data transformation processing so that content can be transformed, from one type of electronic document, for presentation in another type of electronic document. For instance, data transformation suggestions, for transforming content from a first form into a presentation form (second form), may be generated and presented to a user through an improved user interface of an application/service that is used to display the first form of the content. The improved user interface provides a new user interface menu to manage the data transformation suggestions and/or export/import processing of data from one type of electronic document to another. Based on user selection of the confirming data transformation suggestions through the user interface menu, a presentation document is automatically generated on behalf of the user, for example, in a different application/service.

Systems and methods for semi-automated data transformation and presentation of content through adapted user interface

Representative embodiments disclose unique mechanisms to use beacons to provide access to cloud services. In order to access the cloud services a user presents a beacon identifier obtained from a beacon in geographic proximity to a user device used by the user. An authentication service receives the beacon identifier and issues an authentication challenge to the user. Upon successfully completing the authentication challenge, the user is granted access to the cloud service. Authentication challenges can include single factor, two factor, or nominal security challenges. Some embodiments require the device to submit GPS data verifying the location of the device. Some embodiments check user identifying information against a set of approved users. Some embodiments allow a user's device to act as a beacon to access the cloud service. Cloud services can include a wide variety of collaboration, productivity, help, mapping and other services.

Secure private location based services

A switch is provided which is dynamically configurable via a network port thereon. One switch is employed to establish point-to-point electrical connections between devices under test (DUTs) and host devices coupled to upstream ports and downstream ports on the switch respectively. Two switches coupled to a network are employed to facilitate a distributed test lab. DUTs are coupled to upstream ports on a first switch which, based on communication with a test controller over the network, establishes a logical connection between the upstream port coupled to a particular DUT and the network. Host devices are coupled to downstream ports on a second switch which, based on communication with the test controller over the network, establishes a logical connection between the downstream port coupled to a particular host device and the network. A logical connection is also established across the network between the particular DUT and host device.

Dynamically configurable switch for distributed test lab

An apparatus includes a memory unit, a microcontroller, a first communication port providing a first communication path between the apparatus and a computer system, and a second communication port providing a second communication path between the apparatus and a peripheral device. The peripheral device is also communicatively linked with the computer system via a third communication path that bypasses the apparatus. Control of the peripheral device is subject to the apparatus.

Controlling a device connected to first and second communication path wherein device is also connected to third communication path via a bypass link

Growing community of inventors

Bellevue, WA, United States of America

Kaushik Ramaiah Narayanan