Microsoft Technology Licensing, LLC

Tomasz Lukasz Religa

Max Wang

Huitian Jiao

Bernhard Kohlmeier

Madeline Schuster Kleiner

Jignesh Shah

Robert L Rounthwaite

Zhang Li

Nathaniel George Freier

Si-Qing Chen

Ravi Mandliya

Amod Anil Agashe

Tao Ge

Michael Dean Stokes

Geoffrey John Hulten

Cheng Yong Yang

Lei Cui

Furu Wei

Michelle Elena Keslin

Kaushik Ramaiah Narayanan

Curtis Dean Anderson

Jesse Alexander Freitas

Xun Wang

Siqing Chen

Warren Anthony Aldred

Christine Lauren Mayer

Erik Thomas Oveson

Daniel Fairweather

Vincent Etter

Christie Chan

Mari Jean Broman Olsen

Pankaj Gaur

Abhisaar Sharma

Utsab Bose

Weixin Cai

Robert Leslie Rounthwaite

A data processing system obtains source textual content associated with a first writing style and target textual content associated with a second writing style and provides the source textual content as an input to a first machine learning model which analyzes the source content to determine the first writing style of the first textual content. The system provides an indication of the first writing style and the target textual content as an input to a second machine learning model which analyzes the target textual content and rewrites the target textual content according to the first writing style to output updated target textual content rewritten according to the first writing style. Some implementations utilize a single model trained to receive the source textual content, the target textual content, to determine the writing style of the source textual content and rewrite the target textual content according to the first writing style.

Automatic writing style detection and rewriting

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.

Automatic tone detection and suggestion

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

Described herein are mechanisms to allow users to access functionality of applications in a suite of applications. In a first aspect, when a query relating to functionality of an application is received from a user, an index containing both top-level and sub-level functionality is searched. Results are ranked using a trained machine learning model using both context describing user interactions and the search results. A subset of the ranked results are presented to the user as options. In a second aspect the index can comprise entries describing functionality from other applications so that results presented to the user can include cross-application functionality. In a third aspect, the index can be searched using the context prior to receiving a query and adjusting the user interface based on the results. In a fourth aspect, the system can recommend other applications and/or devices that are better suited to a user's intent.

Deep command search within and across applications

A system and method for generating a document control item is described. The system accesses a text document and extracts a portion of the text document. The portion comprises some but not all of the text document. The system sends the portion of the text document to a trained machine learning model and, in response, receives a classification of the portion as demarking a section break. The system modifies the text document by inserting a document control item into the text document at a location of each portion classified as demarking a section break. The system stores the modified document.

Document control item

A system and method and for generating a template based on a page of a document includes receiving a request to create the template for the document, providing a page of the document as an input to a trained machine-learning (ML) model, where the trained machine-learning model is trained to automatically generate target pages for the document based on a received page and the page includes a background image and content, and receiving target pages for the document from the ML model. Each target page has a distinct layout and includes a modified background image and one or more placeholders for content and a template for the document is generated from the one or more target pages and provided for display on a user interface screen associated with the document.

Method and system of generating a document template

A system and method and for monitoring an online meeting includes receiving an indication that the online meeting has been started, retrieving meeting metadata associated with the online meeting, meeting content data from the online meeting, and user data associated with one or more meeting invitees; providing at least one of the meeting metadata, meeting content data and the user data to a machine-learning model for detecting a meeting stage for the online meeting in real-time, determining and based on at least one of the detected meeting stage, meeting content data or the user data that a notification about the online meeting should be provided to one of the meeting invitees, generating data for the notification, and providing the data for the notification for display to the meeting invitee.

Intelligent meeting agent

Technologies are provided for automated generation of revision summaries for an electronic document. In some embodiments, a computing system can determine that a first section of a first version of the electronic document includes changes relative to a second section of a second version of the electronic document. The second section corresponds to the first section. The computing system also can generate respective descriptions of the first section and the second section. The computing system can then generate a summary of the changes by comparing the respective descriptions. The computing system can determine that the summary has a defined placement in a ranking of similarity scores, where a first similarity score in the ranking defines similarity between the respective descriptions. The computing system can add metadata to the first version of the electronic document. The metadata controls presentation of a visual element indicative of the summary within a user interface.

Automated generation of revision summaries

A method and system for providing a personalized user interface and personalized search suggestions when using an application is disclosed. The method includes receiving a request for providing a personalized user interface such as a personalized menu for an application and examining a history of the user's usage of the application, a history of other user's usage of the application, and/or the content of the current document in the application, before identifying one or more suggested options offered by the application based on one or more of these factors. A list may then be generated and provided for being displayed as part of the personalized user interface. Upon receiving an indication of a user's intent to perform a search within the application, the user's usage history, usage history of users with similar activities, and/or content of the current document may be examined to provide the user with a list of search suggestions.

Personalized user experience and search-based recommendations

A computer-implemented technique is described herein for removing sensitive content from documents in a manner that preserves the usefulness of the documents for subsequent analysis. For instance, the technique obscures sensitive content in the documents, while retaining meaningful information in the documents for subsequent processing by a machine-learning engine or other machine-implemented analysis mechanisms. According to one illustrative aspect, the technique removes sensitive content from documents using a modification strategy that is chosen based on one or more selection factors. One selection factor pertains to the nature of the processing that is to be performed on the documents after they have been anonymized.

Removing sensitive content from documents while preserving their usefulness for subsequent processing

Growing community of inventors

Seattle, WA, United States of America

Tomasz Lukasz Religa