Microsoft Technology Licensing, LLC

Yijie Wang

Shaunak Chatterjee

Timothy Paul Jurka

Alexandru Octavian Balan

Souvik Ghosh

Deepak Agarwal

Ajith Muralidharan

Erik Alan Holverson

Boyi Chen

Ying Xuan

Yiping Yuan

Ye Tu

Chun Lo

Sergei Tolmanov

Wei Xue

Bonnie Barrilleaux

Viral Gupta

Yangming Chong

In an example, a plurality of potential feed objects are obtained. An identification of a user performing a navigation command in a user interface is also obtained, the navigation command causing a feed to be displayed or updated. The identification of the user and the plurality of potential feed objects are fed to a machine learned feed object ranking model, the feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects, the score being based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihoods that the user's interaction will cause one or more downstream events by other users, and a value of the one or more downstream events to a social networking service. The plurality of feed objects are ranked by their scores.

Feed optimization

A plurality of potential feed objects and corresponding identifications of actors who performed a user interface action that caused a corresponding potential feed object to be generated are obtained. The plurality of potential feed objects and corresponding actor identifications are then fed into a machine learned feed object ranking model, with the machine learned feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects. The score is based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihood that the user's interaction will cause one or more downstream events by other users, and likelihood that a response from a viewer will cause the actor corresponding to the potential feed object to perform an additional user interface action to generate another potential feed object.

Feed actor optimization

Techniques that modify traditional input devices (e.g., traditional computer mouse form factor) to interact with the virtual reality (VR) devices are described. Such modification allows the VR devices the ability to track the position and orientation of the mouse in the 3 dimensional (3D) VR without requiring extensive complex hardware typically included in VR motion controllers. Specifically, the traditional mouse form factor may be merged with 3D constellation based tracking elements (e.g., LEDs) with minimal form-factor modifications. The constellation tracking elements may include a plurality of fiducial markers on the mouse that may be detected by an imaging sensor, and thus allow tracking with a single imaging sensor (e.g., either head-mounted or fixed position).

Constellation-based augmentation of mouse form-factor for virtual reality applications

In an example embodiment, a machine learned model is used to determine whether to send a notification for a feed object to a user. This machine learned model is optimized not just based on the likelihood that the notification will cause the user to interact with the feed object, but also the likely short-term and long-term impacts of the user interacting with the feed object. This machine learned model factors in not only the viewer's probability of immediate action, such as clicking on a feed object, but also the probability of long-term impact, such as the display causing the viewer to contribute content to the network or the viewer's response encouraging more people to contribute content to the network. As such, the machine learned model is optimized not just on notification interactivity but also on feed objects interactivity.

Joint optimization of notification and feed

In an example embodiment, a GLMix model is utilized that models viewers and actors of feed items. This allows for random effects of individual viewers and actors to be taken into account without introducing biases. Additionally, in an example embodiment, predictions/recommendations are made more accurate by using three models, which are then combined, instead of a single GLMix model. Each of these models has different granularities and dimensions. A global model may model the similarity between user attributes (e.g., from the member profile or activity history) and item attributes. A per-viewer model may model user attributes and activity history of actors on feed items. A per-actor model may model user attributes and activity history of the viewers of feed items. The per-actor model may therefore, rely on information regarding how and what type of viewers interacted with items acted on by the particular actor.

Personalized per-member model in feed

Interactive zones are created in a virtual environment by a head mounted display device executing a virtual reality application. The interactive zones correspond to physical objects that are external to the user such as keyboards, mice, notepads, cups, and other objects that the user may desire to interact with. Each interactive zone includes real time video of the corresponding object so that the user can easily interact with the object, and view their interaction with the object, while still participating in the virtual reality application. If the user moves one of the physical objects, the corresponding interactive zone is also moved in the virtual environment.

Creating interactive zones in virtual environments

A machine for content-feedback-based machine learning to incent online content creation. The machine accesses a relevance value that identifies a level of relevance of a content item to a user. The content item is created by a content creator. The machine generates, using a machine learning model, a feedback sensitivity score associated with the content creator. The machine generates, based on the relevance value and a product between the feedback sensitivity score and a likelihood of the user providing a feedback signal in relation to the content item, a ranking score for the content item. The machine causes display of the content item, based on the ranking score, in a user interface of a client device associated with the user. An input pertaining to the content item received via the user interface causes improvement of the machine learning model based on updating the one or more feedback features.

Growing community of inventors

Sunnyvale, CA, United States of America

Yijie Wang