Microsoft Technology Licensing, LLC

Lan Ye

Shiraz Jitendra Cupala

Neeraj Garg

Eric Jonathan Hull

Ido Priness

Kevin D Morrison

Jaime Brooks Teevan

Adi L Miller

Szymon Madejczyk

Amir Kantor

Shivaram Prabhakar

James Paul Kardos

Kevin Michael Carter

Shlomi Maliah

Shai Ifrach

Yasemin Cenberoglu

Kumud Ranjan

Shyam Gupta

Gautam Jain

Xiao Yan Lu

Alexandre Vicktorovich Grigorovitch

Praful Chavda

Julia Nancy Foran

Matthew Jonathan Gardner

Raj Jain

Eleonora Shtotland

Julia Foran

Gilad Gildin

Ofek David

A system for providing a personalized assistant within a network-based communication service includes one or more processors and a memory storage device storing instructions thereon. During a network-based communication session, the system receives a query from a computing device of a first communication session participant and processes the query by determining that a second communication session participant has shared content via a content sharing feature of the network-based communication service. In response, the system provides the query and at least a portion of the shared content as input to a model, which dynamically constructs a prompt for use as input with a generative language model. The system then presents the prompt as input to the generative language model, receives a response as output from the generative language model, and causes presentation of the response to be presented to the communication session participant.

Network-based communication session copilot

A system for providing a personalized assistant within a network-based communication session includes a processor and a memory storage device storing instructions. The system determines when a first communication session participant joins the network-based communication session after a threshold duration of time subsequent to the start time of the session. Upon determining the first participant has joined, the system obtains content associated with the session and creates request data for a pre-trained generative language model. The request data includes an instruction requesting a predetermined number of suggested utterances not present in the content, each utterance relating to one or more topics corresponding to the content. The system transforms the request data to a command based on a command template and provides the command to the generative language model. The system receives a response from the model, including the predetermined number of suggested utterances, and presents them to the communication session participant in a graphical user interface while the session is in session.

Traditionally, meetings are widely utilized in business and personal communications, whether in-person and/or virtual. Organizing such meetings typically involves multiple exchanges of content and messages between users before, during, and after the meeting. In some cases, meetings may occur impromptu and may result in inefficient and unproductive collaboration. A collaboration object configured to enable users to dynamically collaborate before, during, and after a meeting is provided. In aspects, the collaboration object links content generated before, during, and after the meeting in a single location and provides functionality for concurrent multi-user interaction and synchronization of the content across applications. The collaboration object may be available from a variety of application platforms, enabling and persisting real-time editing and collaboration before, during and after the meeting.

Object for pre- to post-meeting collaboration

Systems and methods for selectively updating or extending built in functionality on a mobile device are disclosed. The updates may be provided to selective portions of software such that the entire software does not need to be replaced. The update may be provided through an application marketplace that provides third party software applications for mobile devices. The software that the mobile device is shipped with may include a number of 'entry points,' which provide functionality that may be extended through the selective updates. When the entry point is triggered by user selection, a determination may be made whether code for the functionality is already available on the mobile device. If not, the mobile device may contact the application marketplace to determine if code is available to provide or extend the requested functionality.

Selective update of core mobile device user interface through application marketplace

Techniques are disclosed herein for changing a user's avatar attributes based on information that is pertinent to the user and that comes from a variety of sources. The user's electronic device may contain a multitude of information about the user, their lifestyle, their current mood, etc. Embodiments provide an application programming interface (API) that allows various applications on the user's electronic device, or elsewhere, to communicate with an avatar platform such that avatar attributes may be changed based on information from a wide variety of applications.

Modifying avatar attributes

A system and method for aggregating and consolidating game notifications is described. In one aspect, game related notifications of different types, from different game sessions, from different games, and from different gaming platforms are aggregated and further consolidated, according to a set of consolidation rules, into a single consolidated environment. The consolidated environment may be projected to and managed from a variety of different gaming devices including mobile devices, gaming and media consoles, and personal computers.

Gaming notifications aggregator

Growing community of inventors

Redmond, WA, United States of America

Lan Ye