Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

A9.com, Inc.

Wei Zhuang

Prashant Singh

Shaunak Chatterjee

Weidong Zhang

Bee-Chung Chen

Yan Ke

Lionel Bitoun

Matthew Hamilton Battles

Grace W Tang

Joel Daniel Young

David J Stein

Boyi Chen

Jingfeng Li

Bryan Thomas Quinn

Paul Taylor Ogilvie

Wenxuan Gao

Amit Chandak

Hung-An Chang

Pavel Dmitriev

Aneesh Agrawal

Michael Helman

Zhihui Xiao

Pratyush Mishra

Vijay Sandeep Damodar Adapala

Rohit Chhapolia

Varnit Agnihotri

Divya Gadde

Ruoyang Wang

Amit Yadav

Yangchun Luo

Ke Wu

Priyanka Gariba

The disclosed embodiments provide a system for processing data. During operation, the system obtains a feature configuration for a feature. Next, the system obtains, from the feature configuration, an anchor containing metadata for accessing the feature in an environment. The system then uses one or more attributes of the anchor to retrieve one or more feature values of the feature from the environment. Finally, the system provides the one or more feature values for use with one or more machine-learning models.

Framework for managing features across environments

Computer-readable media, computer systems, and computing methods for facilitating generation of entity names for entities are provided. The method includes determining a set of previously submitted queries that are associated with an entity. The most frequently used query within the set of previously submitted queries associated with the entity can be identified and, thereafter, designated as the entity name for the entity. The entity name can distinguish the entity from other entities. Such an entity name can be provided for presentation to a user, for example, as a related search suggestion via a search results page.

Generating distinct entity names to facilitate entity disambiguation

Certain embodiments herein relate to dynamically updating a software application to utilize new advertising capabilities or features at runtime. A software application may be developed using libraries in a software development kit (SDK) that include particular functionality related to advertising. As new ad related features become available (such as displaying or handling new ad types or tracking new metrics associated with ads), the new features may be injected or loaded into the application at runtime. Such loading may configure a device running the application to take advantage of the new ad features without re-downloading, reinstalling, or performing other initialization functions associated with the application and/or its library functions.

Techniques for dynamic utilization of advertising capabilities by applications on user devices

Systems, methods, and computer-readable media are disclosed for optimization of ad request fulfillment for mobile device applications. In one embodiment, a system may receive an ad request from a mobile device, and determine a first price point associated with a publisher of the ad request. The system may send a bid request to ad servers, receive a first bid with a first bid amount, and may determine that the first bid amount is a highest bid amount. The system may determine that the first price point is less than the first bid amount, and may send the first bid amount and the first price point to the mobile device, where the mobile device is configured to send the first bid amount and the first price point to a publisher ad server, and the publisher ad server is configured to determine that the first bid amount is a winning bid amount.

Optimization of ad request fulfillment for mobile device applications

An entity summarization system is described herein that mines the Internet and other data source to provide answers to questions such as the relative sentiment of users towards various brands. The system uses a controlled vocabulary list describing a specific aspect of entities of interest. Given an entity name, the system scans the whole content corpus to collect statistics on the words that occur most frequently in the context of the entity name, taking into account proximity information, to produce a weighted list of vocabulary terms describing the entity. Two entities can be compared by normalizing and comparing their weighted term lists. In some embodiments, the system performs these procedures efficiently by leveraging an N-gram web model. Thus, the system provides an automated way to compare two entities to derive information about how users feel about the entities at any given time.

Entity summarization and comparison

Growing community of inventors

Palo Alto, CA, United States of America

Wei Zhuang