Microsoft Technology Licensing, LLC

Other

Prateek Tiwari

Marcelo Medeiros De Barros

Manish Mittal

Vinod Krishnan Koduvayoor Subramanian

Samir Bathla

Ayan Banerjee

Ovidiu Dan

José Carlos Almeida Dos Santos

Naseer Ud Din Ahmed Batt

Shruti Malugu

Guilherme Iscaro De Godoy

Ondrej Starosta

Muhammad Saad Sadiq

Michal Hanzlik

A computing system includes a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving multiple messages from multiple users in a messaging application that supports group conversations, where the multiple messages are included in a group conversation. The acts also include providing a prompt to a generative model, where the prompt includes the multiple messages. The acts additionally include receiving, from the generative model, an output generated by the generative model based upon the prompt and including the output as a turn in the group conversation.

Computer-implemented multi-user messaging application

Systems and methods are provided for determining contextual objects related to web content. Web content may include one or more elements, which may be extracted from the web content and analyzed to identify any contextual objects. The web content elements may be hyperlink elements, and contextual objects may be identified based on the hyperlink elements. A dominant entity may be identified for the web content, and contextual objects relating to the dominant entity may be identified. When a request for web content is received, contextual objects may be provided with the requested content. Personalized contextual objects may be selected from the identified contextual objects based on data associated with the request for web content. Selection of a contextual object may result in navigation to a browsing environment associated with the selected contextual object.

Identifying contextual objects from web content

The present disclosure relates to utilizing a content service system to improve selecting data sources that are used to retrieve digital content items in response to content requests. For example, in response to receiving a content request, the content service system determines to retrieve content items by either calling a lower-quality data source with lower computing costs based on the request having lower service quality metrics or by calling a higher-quality data source with higher computing-costs based on the request having superior service quality metrics. In many instances, the service quality metric is based on the user characteristics of a user identifier associated with the requesting device. By dynamically determining to utilize different data sources having different computing costs based on service quality metrics, the content service system significantly reduces the total amount of computing costs for retrieving and providing digital content, without hurting the user experience.

Determining digital content service quality levels based on customized user metrics

Techniques for optimizing delivery of online content to a mobile client device. In an aspect, a search application on the client device receives a user query, which is submitted to a server over a communications channel. The server retrieves a plurality of ranked search results relevant to the user query, and returns the search results to the client device. The search application further pre-fetches from the server and/or pre-renders content associated with a top plurality of the ranked search results, such that content may be instantly displayed at the client device if requested by the user. The identification and ranking of relevant search results by the server may be performed based on information provided by the client device that is customized to the user and/or the scenario, e.g., user account name, geographical location, device capabilities, etc.

Optimized mobile search

Growing community of inventors

Sammamish, WA, United States of America

Prateek Tiwari