Microsoft Technology Licensing, LLC

Ramya Tridandapani

Michael Jay Gilmore

Alexandre Gueniot

Stephanie Horn

Onur Onder

Eric Minghai Gao

Tyler Robert Adams

Thomas Nhan

Jie Li

Matthew William Kernek

Constance Worsfold Gervais

Thomas R Mignone

Garrett William Brown

Heather Joanne Alekson

Bharat Kumar Ahuja

Michael Alexander Fuller

Chris Welman

Adam Ross Le Doux

Jordan Krissi

Ji Li

Amit Srivastava

Sheng Zhao

Derek Martin Johnson

Gencheng Wu

Konstantin Seleskerov

Aimee Leong

Muin Barkatali Momin

Huey-Ru Tsai

Bohan Li

Sindhu Vigasini Jambunathan

Xinfeng Chen

Stephanie L Horn

Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving an input document and parsing the input document to generate inputs for a natural language generation model using a text analysis model. The natural language generation model generates one or more candidate presentation scripts based on the inputs. A presentation script is selected from the candidate presentation scripts and displayed. A text-to-speech model may be used to generate a synthesized audio presentation of the presentation script. A final presentation may be generated that includes a visual display of the input document and the corresponding audio presentation in sync with the visual display.

Automated script generation and audio-visual presentations

A three-dimensional model can be presented in a two-dimensional digital canvas on a computer display. User input directed at the three-dimensional model in the two-dimensional canvas can be received. The three-dimensional model can be manipulated in response to the user input. A two-dimensional view of the three-dimensional model can be displayed. Corresponding data structures for the model, the canvas, and the two-dimensional objects in the data structure can be maintained and updated. One or more additional techniques can also be utilized in a computer system, such as continuous user-controlled model rotation in a two-dimensional canvas; viewport autofit and non-autofit modes; rotating the model around a camera look-at point; ghosting outside the viewport; normalizing modeling units and values; preset buttons with on-button previews; user-defined view presets; and/or two-dimensional image substitution.

Three-dimensional digital models in two-dimensional digital canvases

Three-dimensional digital modeling with two-dimensional canvas

Three-dimensional model look-at-point rotation and viewport modes

An animation preset graphical user interface (GUI) enables users to select a 3D model of an object and to further select between multiple animation presets that each individually cause a 3D animation engine to apply combinations of animation features against the 3D model. An exemplary animation preset may cause the object to translate across a display area (e.g., move from left to right across screen) while simultaneously rotating against a rotational axis (e.g., spinning so that different surfaces of the object become more prominent). The animation preset GUI may enable the user to dynamically toggle through different intensity levels to cause a selected animation preset to be rendered in accordance with different acceleration parameters and/or magnitude parameters. The animation preset GUI may enable the user to dynamically toggle between predefined animation spaces for animating the object. Animation-parameters may be persisted to a file to enable future editing of the animations.

Animating three-dimensional models using preset combinations of animation features

Growing community of inventors

Sunnyvale, CA, United States of America

Ramya Tridandapani