Microsoft Technology Licensing, LLC

Min Liu

Anthony Vincent Discolo

Michael Dean Stokes

Todd R Manion

Donald F Box

Shiraz Jitendra Cupala

Zhangwei Xu

Curt Andrew Steeb

Jeremy Lee Dewey

Martin James Gudgin

Kean Ee Lim

Edmund Hon-Sum Lui

Ryan B Elgram

Grant Gardner

Jason White

Gilman Kuey Wong

Regis J Crinon

Charles Finkelstein

Richard S Turner, Jr

Po Yuan

Takashi Matsuzawa

Zhen Ma

Yi Zhang

Daniel Buchmueller

Feng Lu

Issa Yousef Khoury

Ashley Speicher

Parvez Ahammad

Yuan Gao

Stacey Law

Haoyun Wu

Todd G Roshak

Mu Qiao

Logananth Seetharaman

Meir Ben Itay

Renaud Bordelet

Hui Wan

Jose D Saura

Ying Wu

Andrei Kozlov

Adam Thomas Mollis

Chris Turkstra

Rathe Hollingum

Shuyin Zhao

Edmund Lui

Jialiang Mao

YinYin Yu

Qian Yao

Karthik Rajkumar

Rina Siller Friedberg

John F McCARTHY, Iii

Shan Ba

Qianqian Ma

Wei Ning

Lisa Qian

Chad K Crowe

Ian V Koeppe

Thomas Meng

Embodiments of the disclosed technologies are capable of providing engagement feedback for an online system while maintaining user privacy. Embodiments determine one or more user groups. A user group includes users, and a size of the user group is selected to protect user privacy. A user action is received from a user in a first group. The user action includes an interaction with a piece of content. A group action count is updated for the first group based on the user action. The group action count indicates a number of interactions with the piece of content by any of the users in the first group. An estimated number of unique engagements is calculated based on the group action count and the size of the first group. The estimated number of unique engagements is provided to the online system as the engagement feedback for the piece of content.

Estimated unique engagement measurement with user privacy protection

Methods, systems, and computer programs are presented for eliminating bias while training an ML model using training data that includes past experimental data. One method includes accessing experiment results, for A/B testing of a first model, that comprise information regarding engagement with a first set of items presented to users, each item being presented within an ordered list of results. A position bias is calculated for positions within the ordered list of results where the items were presented. A machine-learning program is trained to obtain a second model using a training set comprising values for features that include the calculated position bias. The method includes detecting a second set of items to be ranked for presentation to a first user, and calculates, using the second model, a relevance score for the second set of items, which are ranked based on the respective relevance score and presented on a display.

Position-bias correction for predictive and ranking systems

A delayed grouping (batch) processing of previous campaign delivery pacing decisions and corresponding outcomes (deliveries) is used to configure a new auction experiment iteration. In the new iteration, a campaign that was previously over-delivered is classified as either (a) over-delivered due to incorrect pacing or (b) over-delivered due to auction experiment design. After the delayed processing, the new auction experiment iteration is conducted with a mitigating action taken on the previously over-delivered campaign if the campaign is classified as (b) over-delivered due to auction experiment design. For example, the mitigating action can include removing the campaign from a subsequent iteration of the experiment, or the experiment can be redesigned. By doing so, the over-delivery caused by the campaign due to the auction experiment design is avoided when performing the new auction experiment iteration.

Delayed processing for over-delivery determination for content delivery system experimentation

Device linking is described. In one or more implementations, data is maintained at a network service that describes characteristics of a plurality of devices that are associated with a user account of the network service. A communication is formed to be received by one of the plurality of devices that includes a portion of the data that pertains to another one of the plurality of devices and that is suitable by the receiving device to discover the other one of the plurality of devices to initiate a local network connection between the devices.

Device linking

An integrated gaming and media experience is disclosed, including television viewing on a gaming console. A client component is installed via a bootstrap process that uses authentication information to accomplish this task. Once installed, it integrates itself into a typical gaming display. Various console hardware details are used to enable communication between the client component and downstream servers providing the content. Once up and running, the client component allows users to watch television as if they were interacting with a set-top box. Users may switch between various applications on the gaming console, including but not limited to game titles, DVR, VOD, DVD programs, and so on.

Television viewing on gaming consoles

Systems, methods, and computer-readable media for responding to a search query with search results ranked according to interest circles of a plurality of computer users are presented. Interest circles are formed from a computer user's navigation data, including the computer user's navigation history. A search query is received from a requesting computer user. The search query is directed to a query topic or set of query topics. A set of search results responsive to the search query are obtained. A plurality of computer users, each of the plurality of computer users having an established interest circle corresponding to the query topic, is identified. The set of search results are then ordered according to the interest circles of the identified plurality of computer users. Thereafter, the higher ordered search results are returned to the requesting computer user in response to the search query.

Search results through interest circles

A system is disclosed for media content search and retrieval, and a virtual television channel capable of using that system. The present system may be implemented on a computing device, such as for example a media service server, and a client device, such as for example a set top box for a television system, a mobile telephone, a personal digital assistant or a gaming console. A first aspect of the present system relates to a media download control engine which enables a client device with limited capabilities to play media content which comes from a website in a format not supported by the client device. A second aspect of the present system may make use of the media download control engine to obtain media content and create customized virtual channels. The second aspect in particular relates to a virtual channel engine that schedules a continuous stream of content for the user, which content is selected based on topics of interest to the user.

Media content retrieval system and personal virtual channel

Television content from multiple sources is described. In embodiment(s), a television client device includes an interface to receive television media content in multiple streaming video formats. A television media service implemented in the television client device can process television media content when received in a first streaming video format, and render the television media content for display. In addition, the television media service can process additional television media content when received in a second streaming video format, and render the additional television media content for display.

Television content from multiple sources

A system, media, and method for transforming a main image of a digital image in accordance with a parameter are provided. The main image that is transformed based on the parameter may be one stored in the Exchangeable Image File ('EXIF') format. In turn, the metadata, including the thumbnail image, is updated to correspond to the transformed main image. The transformed main image and updated metadata are stored together in a file using the EXIF format. Thus, the transformed main image may be viewed using a digital camera or viewer software compatible with a properly formatted EXIF file.

Transformation of EXIF images

Techniques and tools for analyzing and adjusting the exposure of digital images are described. For example, a computer processes a digital image by analyzing exposure data, assigning an image classification (e.g., StretchNeeded, UnderExposed, OverExposed, or Normal) based on the analysis, and selecting an exposure compensation technique (e.g., histogram stretch, positive gamma curve, negative gamma curve, or no adjustment) based on the image classification. The exposure data can be luminance values for pixels in the digital image represented in a histogram. The computer can produce transform data comprising a transformation of the exposure data according to the selected exposure compensation technique. The computer can store transform data in a look-up table and can store the look-up table in the digital image file. The described techniques and tools can be implemented as a feature of an operating system environment and can be activated responsive to user action via a user interface.

Automatic analysis and adjustment of digital images with exposure problems

Systems and methods are described herein for automatically installing and using media processing filters to extend the media functionality of system processes. A system service is requested by the add-in filter to be installed on the system. The filter management service processes the request and installs the filters to be invoked later by other system processes such as device drivers, applications and acquisition software. The system processes use the filter management service to enumerate filters available on the system and select one or more of the filters to extend their media functionality. The filters are objects that may be used by multiple processes at any given time. Also, the filter management service can validate trustworthiness of a filter prior to installing the filter on the system. Additionally, the filter management service can be used to provide selected filters to be invoked from a process separate from the process requesting the filter for use. The installed filters may be searched and enumerated according to their associated categories.

System architecture and related methods for dynamically adding software components to extend functionality of system processes

Validating a color that is selected in an authoring environment for display in a destination media environment includes selecting a color for an application, converting the values of the color to those in a fundamental color space, and converting the values from the fundamental color space to those in a color space corresponding to the destination media environment. Validity of the selected color in the destination media environment depends on the component values in the destination media environment being within an acceptable range of values.

Picking TV safe colors

Growing community of inventors

Redmond, WA, United States of America

Min Liu