Microsoft Technology Licensing, LLC

Itai Almog

Parthasarathy Sundararajan

Eric Norman Badger

Timothy S Paek

Dmytro Rudchenko

Drew Elliott Linerud

Tim Paek

Shawna Julie Davis

Asela J Gunawardana

Jason Anthony Grieves

Tirthankar Sengupta

Kenneth R Walters

Andrew Douglas Peterson

March Rogers

Christian James Colando

Ron Mondri

Francois M Rouaix

Jerome Joseph Turner

Palmer H Batt

Fan Zhong

Kozo Miyano

Masahiro Ami

Erez Kikin Gil

Liang Jeff Chen

Arthur Zavalkovsky

Clea H Allington

Juan Dai

Eduardo Sonnino

Donovan P Lange

Chad Erik Fowler

Taketoshi Yoshida

Ganapathy V Raman

Timothy Seung Yoon Paek

Tomer Shiran

Keith Arthur Fournier, Ii

Chit Wei Saw

Drew Elliot Linerud

Songming Ho

Dhruv Kochhar

Shubham Goyal

Jairo Medina Garcia

Gleb Krivosheev

Nick Barnwell

Songming He

Ryan Levick

James H Cook

Donovan Paul Lange

Keith Arthur Ii Fournier

Manuel Garcia Fierro

Gleb G Krivosheev

A data processing system implements receiving content and a call requesting a generative model to generate a video summary of the content; constructing a prompt including the content and instructions to the model to identify semantic context of the content, to identify a text data item, an audio data item, and/or a video data item embedded in the content to generate a text transcript of the audio data item and/or the video data item, or a textual description of the video data item, to summarize the text data item, the text transcripts, and/or the textual description as a summary of the content based on the semantic context, and to generate the video summary based on the summary and a portion of the text data item, the audio data item, and/or the video data item; providing the first prompt to the generative model; providing the video summary to a client device for presentation.

AI-based video summary generation for content consumption

Dynamic templates include regions that provide behavior based upon a purpose or desired outcome. Templates and regions can modify the logical representations associated with objects to create semantic context for the objects. Templates and regions can also generate visual representations of objects based upon their logical representations. The visual representation utilized by a template or region can be selected manually or based upon the capabilities of a computing device. Objects contained within regions can be sorted, filtered, arranged, and projected based on their associated logical representations. Templates and regions can modify their size based upon the objects contained therein, can receive logical representations of objects from data sources and update the data sources to reflect modification of the logical representations, can initiate actions based on changes to the logical representations associated with objects, and generate structured summaries or other types of content based upon the logical representations.

Dynamic whiteboard regions

Dynamic whiteboard templates

A notes service receives note items produced by various software applications. Each of the note items may comprise metadata, context data, and content representative of a note. The notes service, for each of the note items, stores a given note item in a note repository and updates a graph based at least on the metadata, the context data, and the content for the given note. As the notes service receives queries from the various software applications obtain relevant ones of the note items from the note repository, the service searches the graph for one or more note items relevant to a given query. The one or more notes are retrieved from the repository and provided in reply to the requesting application.

Systems, methods, and software for implementing a notes service

Apparatus and methods are disclosed for providing feedback and guidance to touch screen device users to improve the text entry user experience and performance. According to one embodiment, a method comprises receiving a text entry, receiving input on a touch screen in the form of a first single touch input located over a word of previously entered text, and presenting the user with one or more suggestion candidates indicated possible replacement words related to the selected word. The user can then select one of the suggestion candidates using a second single touch input to replace the selected word with a word associated with the selected suggestion candidate.

Typing assistance for editing

An apparatus and method are disclosed for providing feedback and guidance to touch screen device users to improve text entry user experience and performance by generating input history data including character probabilities, word probabilities, and touch models. According to one embodiment, a method comprises receiving first input data, automatically learning user tendencies based on the first input data to generate input history data, receiving second input data, and generating auto-corrections or suggestion candidates for one or more words of the second input data based on the input history data. The user can then select one of the suggestion candidates to replace a selected word with the selected suggestion candidate.

User-centric soft keyboard predictive technologies

In a mobile device, the text entered by users is analyzed to determine a set of responses commonly entered by users into text applications such as SMS applications in response to received messages. This set of responses is used to provide suggested responses to a user for a currently received message in a soft input panel based on the text of the currently received message. The suggested responses are provided before any characters are provided by the user. After the user provides one or more characters, the suggested responses in the soft input panel are updated. The number of suggested responses displayed to the user in the soft input panel is limited to a total confidence value to reduce user distraction and to allow for easier selection. An undo feature for inadvertent selections of suggested responses is also provided.

String prediction

Smart reminders are generated from input according to lexical and contextual cues. The input may be entered into any suitable application via any suitable electronic device. The input may be processed by a natural language processor to determine whether to convert the input into a smart reminder. In this way, the input of the note may be parsed to identify entities, such as entities associated with one or more people, relevant time(s), action(s), instruction(s), etc., for creating the smart reminder. The identified entities may then be used as triggers for displaying the smart reminder at an appropriate time to a user. A trigger such as detecting a person associated with the input, e.g., by receiving an incoming call from the person, connecting to the same network as the person, receiving a text from the person, or detecting the voice of the person, may cause the smart reminder to be displayed.

Smart reminder generation from input

In a mobile device, a context is determined for the mobile device. The context is determined based on a variety of characteristics of the mobile device environment including, for example, the current application being used, any contacts that a user of the mobile device is interacting with or having a conversation with, the current date and/or time, a current topic of the conversation, a current style of the conversation, etc. Based on a set of strings associated with the determined context and user generated text, one or more string predictions are generated for the user generated text. The string predictions may be presented to the user as suggested completions of the user generated text.

Generating string predictions using contexts

Embodiments provide context-aware inclusion of emoticon item sets in applications and/or services. The emoticon item sets include a plurality of emoticon images or other emoticons. A computing device creates custom emoticon item sets for each of the applications. Based on a determined execution context, the computing device selects the emoticon item set and presents the selected emoticon item set for use within the execution context by a user of the computing device.

Creation and context-aware presentation of customized emoticon item sets

The collection and clustering of data input characteristics from a plurality of computing devices is provided. The clustered data input characteristics define user groups to which users are assigned. Input models such as language models and touch models are created for, and distributed to, each of the user groups based on the data input characteristics of the users assigned thereto. For example, an input model may be selected for a computing device based on a current context of the computing device. The selected input model is applied to the computing device during the current context to alter the interpretation of input received from the user via the computing device.

Clustering crowdsourced data to create and apply data input models

Growing community of inventors

Redmond, WA, United States of America

Itai Almog